Benchmarks run by ByteOrbital on our own hardware; written with AI assistance from our results.

The RTX 2000E Ada Generation is a workstation card with 16 GB of memory, a 50 W power limit and a low-profile form factor. That makes it one of the few discrete GPUs that fits a compact machine such as our Minisforum MS-02 Ultra. We own the machine and the card, use them daily, and ran our benchmark suite with the card as the main accelerator. The question is simple: how much local AI does 50 W and 16 GB actually buy?

Prefer to watch? Nova and Dex walk through every result in our five-minute video on YouTube.

How we tested

What fits in 16 GB

Memory decides what a card can do before speed does, so start there.

Specifications
Llama 3.1 8B Instruct Q4_K_M (4.9 GB)Fits on the card
Qwen3 14B Q4_K_M (9.0 GB)Fits on the card
gpt-oss-20b MXFP4 (12.1 GB)Fits on the card
Qwen3 30B-A3B Q4_K_M (18.6 GB)Needs CPU offload (not run by default)
Llama 3.3 70B Instruct Q4_K_M (42.5 GB)Does not fit
gpt-oss-120b MXFP4 (63.4 GB)Does not fit

The card's memory is 16,380 MiB. In practice, a model of about 12 GB leaves modest room for context, and the 18.6 GB mixture-of-experts model is already out of reach without offloading to the CPU. For comparison, the Ryzen AI Max+ 395 machine in our other tests holds all six, including the 63.4 GB model, because it shares a large memory pool.

8060S ROCm runs gpt-oss-120b MXFP4; RTX 2000E Ada can't fit it

llama.cpp llama-bench. On gpt-oss-120b MXFP4: 8060S ROCm 56.3 vs 8060S Vulkan 53.9. · tokens per second · higher is better

+3.4% vs 8060S Vulkan 8060S ROCm leads in 6 of 6

020406080100Llama 3.1 8BInstruct Q4_K_MQwen3 14B Q4_K_Mgpt-oss-20b MXFP4Qwen3 30B-A3B Q4_K_M(MoE)Llama 3.3 70BInstruct Q4_K_Mgpt-oss-120b MXFP46.8942.242.323.246.344.63.6422.719.212.825.624.89.1164.361.240.279.475.914.442.99291.15.315.2856.353.9
View data table
8060S ROCm runs gpt-oss-120b MXFP4; RTX 2000E Ada can't fit it: values in tokens per second
SeriesTestValue (tokens per second)RunsMin to maxVersionCommand
285HX CPULlama 3.1 8B Instruct Q4_K_M6.8916.89 to 6.89llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -ngl 0 -m /var/tmp/bo-bench/models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
285HX CPUQwen3 14B Q4_K_M3.6413.64 to 3.64llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -ngl 0 -m /var/tmp/bo-bench/models/Qwen3-14B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
285HX CPUgpt-oss-20b MXFP49.1119.11 to 9.11llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -ngl 0 -m /var/tmp/bo-bench/models/gpt-oss-20b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
285HX CPUQwen3 30B-A3B Q4_K_M (MoE)14.4114.4 to 14.4llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -ngl 0 -m /var/tmp/bo-bench/models/Qwen3-30B-A3B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
RTX 2000E AdaLlama 3.1 8B Instruct Q4_K_M42.2142.2 to 42.2llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -fa 1 -m /var/tmp/bo-bench/models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
RTX 2000E AdaQwen3 14B Q4_K_M22.7122.7 to 22.7llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -fa 1 -m /var/tmp/bo-bench/models/Qwen3-14B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
RTX 2000E Adagpt-oss-20b MXFP464.3164.3 to 64.3llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -fa 1 -m /var/tmp/bo-bench/models/gpt-oss-20b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
RTX 2000E Ada - ada_cudaLlama 3.1 8B Instruct Q4_K_M42.3142.3 to 42.3llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -fa 1 -m /var/tmp/bo-bench/models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
RTX 2000E Ada - ada_cudaQwen3 14B Q4_K_M19.2119.2 to 19.2llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -fa 1 -m /var/tmp/bo-bench/models/Qwen3-14B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
RTX 2000E Ada - ada_cudagpt-oss-20b MXFP461.2161.2 to 61.2llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)LD_LIBRARY_PATH=/opt/cuda-12.8/lib64:/opt/bo-bench/llama.cpp-b12300-cuda/bin /opt/bo-bench/llama.cpp-b12300-cuda/bin/llama-bench -fa 1 -m /var/tmp/bo-bench/models/gpt-oss-20b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
Ryzen 395 CPULlama 3.1 8B Instruct Q4_K_M23.2123.2 to 23.2llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -ngl 0 -m /models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
Ryzen 395 CPUQwen3 14B Q4_K_M12.8112.8 to 12.8llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -ngl 0 -m /models/Qwen3-14B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
Ryzen 395 CPUgpt-oss-20b MXFP440.2140.2 to 40.2llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -ngl 0 -m /models/gpt-oss-20b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
Ryzen 395 CPUQwen3 30B-A3B Q4_K_M (MoE)42.9142.9 to 42.9llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -ngl 0 -m /models/Qwen3-30B-A3B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S ROCmLlama 3.1 8B Instruct Q4_K_M46.3146.3 to 46.3llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-10.0-strix-llama_20261102T063225 llama-bench -fa 1 -m /models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S ROCmQwen3 14B Q4_K_M25.6125.6 to 25.6llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-10.0-strix-llama_20261102T063225 llama-bench -fa 1 -m /models/Qwen3-14B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S ROCmgpt-oss-20b MXFP479.4179.4 to 79.4llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-10.0-strix-llama_20261102T063225 llama-bench -fa 1 -m /models/gpt-oss-20b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S ROCmQwen3 30B-A3B Q4_K_M (MoE)92192 to 92llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-10.0-strix-llama_20261102T063225 llama-bench -fa 1 -m /models/Qwen3-30B-A3B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S ROCmLlama 3.3 70B Instruct Q4_K_M5.3115.31 to 5.31llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-10.0-strix-llama_20261102T063225 llama-bench -fa 1 -m /models/Llama-3.3-70B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S ROCmgpt-oss-120b MXFP456.3156.3 to 56.3llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/kfd --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:rocm-10.0-strix-llama_20261102T063225 llama-bench -fa 1 -m /models/gpt-oss-120b/gpt-oss-120b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S VulkanLlama 3.1 8B Instruct Q4_K_M44.6144.6 to 44.6llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -fa 1 -m /models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S VulkanQwen3 14B Q4_K_M24.8124.8 to 24.8llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -fa 1 -m /models/Qwen3-14B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S Vulkangpt-oss-20b MXFP475.9175.9 to 75.9llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -fa 1 -m /models/gpt-oss-20b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S VulkanQwen3 30B-A3B Q4_K_M (MoE)91.1191.1 to 91.1llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -fa 1 -m /models/Qwen3-30B-A3B-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S VulkanLlama 3.3 70B Instruct Q4_K_M5.2815.28 to 5.28llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -fa 1 -m /models/Llama-3.3-70B-Instruct-Q4_K_M.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
8060S Vulkangpt-oss-120b MXFP453.9153.9 to 53.9llama.cpp b12300 (ms01 CUDA build, sm_89); ms03 kyuz0 toolbox images pinned in hosts.yaml (~b12297)podman run --rm --device /dev/dri --group-add keep-groups --security-opt seccomp=unconfined -v /srv/models:/models:ro docker.io/kyuz0/amd-strix-halo-toolboxes:vulkan-radv-performance_20261101T205203 llama-bench -fa 1 -m /models/gpt-oss-120b/gpt-oss-120b-MXFP4.gguf -p 512 -n 128 -d 0,4096,16384,32768 -r 3 -o json 2>/var/tmp/bo-bench/llama.err || { tail -5 /var/tmp/bo-bench/llama.err; exit 1; }
Caveatms01: RAM runs at 4800 MT/s, rated 5600 MT/s (2 x 32 GB DDR5). Memory bandwidth and CPU-side LLM numbers are measured at the configured speed, not the rated one.

Series with no bar for a model could not fit it (see what_fits in findings.json).

Local LLM speed

Here are the llama.cpp results with the card, from the default run and the dedicated ada_cuda run.

Specifications
Llama 3.1 8B generation42.2 tok/s (default), 42.3 tok/s (ada_cuda)
Llama 3.1 8B prompt processing1,849 tok/s (default), 1,852 tok/s (ada_cuda)
Qwen3 14B generation22.7 tok/s (default), 19.2 tok/s (ada_cuda)
Qwen3 14B prompt processing954 tok/s (default), 898 tok/s (ada_cuda)
gpt-oss-20b generation64.3 tok/s (default), 61.2 tok/s (ada_cuda)
gpt-oss-20b prompt processing1,625 tok/s (default), 1,957 tok/s (ada_cuda)

Do not read too much into the gaps between those two columns. Both runs used the same card, so any difference is run-to-run variation plus whatever else the machine was doing. The two configurations disagreed by +20% on gpt-oss-20b prompt processing and by -15% on Qwen3 14B generation, and the Llama 3.1 8B results matched to within 1%. Each is a single run. Treat the card as roughly 40 tok/s on an 8B model, 20 on a 14B and 60 on gpt-oss-20b.

Context length costs speed. At 32k of context, gpt-oss-20b generation falls from 64.3 to 51.1 tok/s on the default run, and Llama 3.1 8B falls from 42.2 to 17.6 tok/s. Prompt processing on gpt-oss-20b drops from 1,625 to 1,029 tok/s over the same range.

Against the CPU in the same machine the card is the difference between usable and not. The Core Ultra 9 285HX manages 6.89 tok/s on Llama 3.1 8B, 3.64 on Qwen3 14B and 9.11 on gpt-oss-20b, against 42.2, 22.7 and 64.3 tok/s on the card.

Speech, rendering and video

Whisper large-v3-turbo transcribes at 15.2x real time on CUDA in the default run and 16.0x in the ada_cuda run, against 2.68x and 2.71x on the CPU. The Ryzen AI Max+ 395 machine's CPU alone reaches 3.78x, so the card's gain over any CPU here is large.

In Blender, the BMW scene renders in 26.9 s on CUDA and 27.1 s in the ada_cuda run, which is level. With OptiX it takes 13.0 s, so use OptiX if your renderer supports it.

MS-02 Ultra and MS-02 Ultra - ada_cuda are level on Blender GPU rendering (bmw27)

bo-bench blender gpu. · s · lower is better

+0.6% vs MS-02 Ultra - ada_cuda MS-02 Ultra leads in 1 of 2

0102030cudaoptix26.927.113
View data table
MS-02 Ultra and MS-02 Ultra - ada_cuda are level on Blender GPU rendering (bmw27): values in s
SeriesTestValue (s)RunsMin to maxStd devVersionCommand
MS-02 Ultracuda26.9226.9 to 270.078Blender 5.2.4; scenes bmw27 / classroom / monsterfor s in bmw27 classroom monster; do t=$(/opt/bo-bench/blender-5.2.4-linux-x64/blender -b /var/tmp/bo-bench/assets/scene-$s/$s/main.blend -noaudio -o /var/tmp/bo-bench/bout/f_#### -E CYCLES --python /var/tmp/bo-bench/blender_dev.py -f 1 -- CUDA 2>&1 | grep -oE 'Time: [0-9]+:[0-9.]+ \(Saving' | tail -1 | sed -E 's/Time: ([0-9]+):([0-9.]+).*/\1 \2/' | awk '{print $1*60+$2}') echo "BO_SCENE $s $t" done
MS-02 Ultra - ada_cudacuda27.1227 to 27.20.149Blender 5.2.4; scenes bmw27 / classroom / monsterfor s in bmw27 classroom monster; do t=$(/opt/bo-bench/blender-5.2.4-linux-x64/blender -b /var/tmp/bo-bench/assets/scene-$s/$s/main.blend -noaudio -o /var/tmp/bo-bench/bout/f_#### -E CYCLES --python /var/tmp/bo-bench/blender_dev.py -f 1 -- CUDA 2>&1 | grep -oE 'Time: [0-9]+:[0-9.]+ \(Saving' | tail -1 | sed -E 's/Time: ([0-9]+):([0-9.]+).*/\1 \2/' | awk '{print $1*60+$2}') echo "BO_SCENE $s $t" done
MS-02 Ultra - ada_cudaoptix13212.9 to 130.064Blender 5.2.4; scenes bmw27 / classroom / monsterfor s in bmw27 classroom monster; do t=$(/opt/bo-bench/blender-5.2.4-linux-x64/blender -b /var/tmp/bo-bench/assets/scene-$s/$s/main.blend -noaudio -o /var/tmp/bo-bench/bout/f_#### -E CYCLES --python /var/tmp/bo-bench/blender_dev.py -f 1 -- OPTIX 2>&1 | grep -oE 'Time: [0-9]+:[0-9.]+ \(Saving' | tail -1 | sed -E 's/Time: ([0-9]+):([0-9.]+).*/\1 \2/' | awk '{print $1*60+$2}') echo "BO_SCENE $s $t" done
Caveatms01: RAM runs at 4800 MT/s, rated 5600 MT/s (2 x 32 GB DDR5). Memory bandwidth and CPU-side LLM numbers are measured at the configured speed, not the rated one.

For video encoding, NVENC does 371 fps for HEVC, 322 fps for H.264 and 393 fps for AV1 on our 1080p test clip. The surprise is the Intel iGPU in the same machine: its VAAPI encoder does 451 fps for HEVC and 414 fps for H.264 in the ada_cuda configuration, and 427 and 400 fps in the igpu_arc one. If you only need H.264 or HEVC, you do not need this card for encoding. AV1 is the reason to use NVENC here. For scale, the OneXStation's VAAPI HEVC encoder reaches 755 fps.

OneXStation (8060S) tops hardware video encoding: 755 fps (vaapi_hevc)

Big Buck Bunny 1080p, 60 s source. · fps · higher is better

+4.6% vs MS-02 Ultra - igpu_arc MS-02 Ultra - ada_cuda leads in 2 of 7

0200400600800nvenc_hevcintel_vaapi_h…intel_vaapi_h…nvenc_h264nvenc_av1vaapi_h264vaapi_hevc371371389414400405451427322393441755
View data table
OneXStation (8060S) tops hardware video encoding: 755 fps (vaapi_hevc): values in fps
SeriesTestValue (fps)RunsMin to maxStd devVersionCommand
MS-02 Ultranvenc_hevc3713368 to 3711.97distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -c:v hevc_nvenc -preset p5 -b:v 6M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultraintel_vaapi_h2643893387 to 4017.69distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v h264_vaapi -b:v 8M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultraintel_vaapi_hevc4053397 to 42413.6distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v hevc_vaapi -b:v 6M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - ada_cudanvenc_hevc3713369 to 3711.51distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -c:v hevc_nvenc -preset p5 -b:v 6M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - ada_cudaintel_vaapi_h2644143409 to 4258.19distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v h264_vaapi -b:v 8M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - ada_cudaintel_vaapi_hevc4513451 to 4668.73distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v hevc_vaapi -b:v 6M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - ada_cudanvenc_h2643223319 to 3221.36distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -c:v h264_nvenc -preset p5 -b:v 8M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - ada_cudanvenc_av13933392 to 3930.556distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -c:v av1_nvenc -preset p5 -b:v 5M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - igpu_arcintel_vaapi_h2644003398 to 4127.76distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v h264_vaapi -b:v 8M -f null - 2>&1 | tr '\r' '\n'
MS-02 Ultra - igpu_arcintel_vaapi_hevc4273414 to 44113.4distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v hevc_vaapi -b:v 6M -f null - 2>&1 | tr '\r' '\n'
OneXStation (8060S)vaapi_h2644413441 to 4420.435distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v h264_vaapi -b:v 8M -f null - 2>&1 | tr '\r' '\n'
OneXStation (8060S)vaapi_hevc7553754 to 7571.6distro ffmpeg (see inventory)ffmpeg -hide_banner -benchmark -y -t 60 -i /var/tmp/bo-bench/assets/bbb-clip/bbb_1080p_60s.mp4 -an -vaapi_device /dev/dri/renderD128 -vf format=nv12,hwupload -c:v hevc_vaapi -b:v 6M -f null - 2>&1 | tr '\r' '\n'
Caveatms01: RAM runs at 4800 MT/s, rated 5600 MT/s (2 x 32 GB DDR5). Memory bandwidth and CPU-side LLM numbers are measured at the configured speed, not the rated one.

Power and heat

Under sustained GPU load, the card averaged 49 W and sat at its limit for the whole run, which in the chart lasts about 11.6 minutes. Its temperature climbed from 46 °C to a 79 °C peak and held there.

RTX 2000E Ada - ada_cuda peaks at 79°C under sustained GPU load

GPU temperature while the test holds the load (1 second samples). · °C · lower is better

4050607080115.623.939.646.962.669.985.593.9108.5116.8132.5139.8155.4162.7178.4186.8201.4209.7225.4241248.3264271.3286.9295.3309.9318.3333.9341.2356.9364.2379.8388.2402.8411.1426.7434.1449.7457472.7488.3496.7511.3519.6535.3542.6558.2565.5581.2589.5604.1612.5628.1635.4651.1658.4674.1682.469779
View data table
RTX 2000E Ada - ada_cuda peaks at 79°C under sustained GPU load: values in °C
SeriesxValue (°C)
RTX 2000E Ada - ada_cuda146
RTX 2000E Ada - ada_cuda15.661
RTX 2000E Ada - ada_cuda23.965
RTX 2000E Ada - ada_cuda39.669
RTX 2000E Ada - ada_cuda46.971
RTX 2000E Ada - ada_cuda62.672
RTX 2000E Ada - ada_cuda69.973
RTX 2000E Ada - ada_cuda85.574
RTX 2000E Ada - ada_cuda93.974
RTX 2000E Ada - ada_cuda108.575
RTX 2000E Ada - ada_cuda116.875
RTX 2000E Ada - ada_cuda132.576
RTX 2000E Ada - ada_cuda139.876
RTX 2000E Ada - ada_cuda155.476
RTX 2000E Ada - ada_cuda162.776
RTX 2000E Ada - ada_cuda178.477
RTX 2000E Ada - ada_cuda186.877
RTX 2000E Ada - ada_cuda201.477
RTX 2000E Ada - ada_cuda209.777
RTX 2000E Ada - ada_cuda225.477
RTX 2000E Ada - ada_cuda24177
RTX 2000E Ada - ada_cuda248.377
RTX 2000E Ada - ada_cuda26477
RTX 2000E Ada - ada_cuda271.377
RTX 2000E Ada - ada_cuda286.977
RTX 2000E Ada - ada_cuda295.378
RTX 2000E Ada - ada_cuda309.978
RTX 2000E Ada - ada_cuda318.378
RTX 2000E Ada - ada_cuda333.978
RTX 2000E Ada - ada_cuda341.278
RTX 2000E Ada - ada_cuda356.978
RTX 2000E Ada - ada_cuda364.278
RTX 2000E Ada - ada_cuda379.878
RTX 2000E Ada - ada_cuda388.278
RTX 2000E Ada - ada_cuda402.878
RTX 2000E Ada - ada_cuda411.178
RTX 2000E Ada - ada_cuda426.778
RTX 2000E Ada - ada_cuda434.178
RTX 2000E Ada - ada_cuda449.778
RTX 2000E Ada - ada_cuda45778
RTX 2000E Ada - ada_cuda472.778
RTX 2000E Ada - ada_cuda488.378
RTX 2000E Ada - ada_cuda496.778
RTX 2000E Ada - ada_cuda511.378
RTX 2000E Ada - ada_cuda519.678
RTX 2000E Ada - ada_cuda535.378
RTX 2000E Ada - ada_cuda542.678
RTX 2000E Ada - ada_cuda558.278
RTX 2000E Ada - ada_cuda565.578
RTX 2000E Ada - ada_cuda581.278
RTX 2000E Ada - ada_cuda589.579
RTX 2000E Ada - ada_cuda604.179
RTX 2000E Ada - ada_cuda612.579
RTX 2000E Ada - ada_cuda628.179
RTX 2000E Ada - ada_cuda635.479
RTX 2000E Ada - ada_cuda651.179
RTX 2000E Ada - ada_cuda658.479
RTX 2000E Ada - ada_cuda674.179
RTX 2000E Ada - ada_cuda682.479
RTX 2000E Ada - ada_cuda69779
Caveatms01: RAM runs at 4800 MT/s, rated 5600 MT/s (2 x 32 GB DDR5). Memory bandwidth and CPU-side LLM numbers are measured at the configured speed, not the rated one.

Samples are thinned to about 90 points for the chart; the full 1 second series is in the run's samples file.

Thinned further to 60 points for the article page; every kept point is an original sample.

RTX 2000E Ada - ada_cuda averages 49 W under sustained GPU load

GPU power draw while the test holds the load (1 second samples). · watts · higher is better

0204060115.623.939.646.962.669.985.593.9108.5116.8132.5139.8155.4162.7178.4186.8201.4209.7225.4241248.3264271.3286.9295.3309.9318.3333.9341.2356.9364.2379.8388.2402.8411.1426.7434.1449.7457472.7488.3496.7511.3519.6535.3542.6558.2565.5581.2589.5604.1612.5628.1635.4651.1658.4674.1682.469749.9
View data table
RTX 2000E Ada - ada_cuda averages 49 W under sustained GPU load: values in watts
SeriesxValue (watts)
RTX 2000E Ada - ada_cuda17.02
RTX 2000E Ada - ada_cuda15.650
RTX 2000E Ada - ada_cuda23.950
RTX 2000E Ada - ada_cuda39.650.1
RTX 2000E Ada - ada_cuda46.950.5
RTX 2000E Ada - ada_cuda62.649.9
RTX 2000E Ada - ada_cuda69.950.1
RTX 2000E Ada - ada_cuda85.549.9
RTX 2000E Ada - ada_cuda93.949.9
RTX 2000E Ada - ada_cuda108.550
RTX 2000E Ada - ada_cuda116.849.9
RTX 2000E Ada - ada_cuda132.549.9
RTX 2000E Ada - ada_cuda139.850
RTX 2000E Ada - ada_cuda155.449.9
RTX 2000E Ada - ada_cuda162.750
RTX 2000E Ada - ada_cuda178.449.9
RTX 2000E Ada - ada_cuda186.849.9
RTX 2000E Ada - ada_cuda201.449.9
RTX 2000E Ada - ada_cuda209.749.9
RTX 2000E Ada - ada_cuda225.449.9
RTX 2000E Ada - ada_cuda24150
RTX 2000E Ada - ada_cuda248.350
RTX 2000E Ada - ada_cuda26449.9
RTX 2000E Ada - ada_cuda271.350
RTX 2000E Ada - ada_cuda286.949.9
RTX 2000E Ada - ada_cuda295.349.9
RTX 2000E Ada - ada_cuda309.949.9
RTX 2000E Ada - ada_cuda318.349.9
RTX 2000E Ada - ada_cuda333.950
RTX 2000E Ada - ada_cuda341.250
RTX 2000E Ada - ada_cuda356.949.9
RTX 2000E Ada - ada_cuda364.249.9
RTX 2000E Ada - ada_cuda379.849.9
RTX 2000E Ada - ada_cuda388.250
RTX 2000E Ada - ada_cuda402.849.9
RTX 2000E Ada - ada_cuda411.150
RTX 2000E Ada - ada_cuda426.749.9
RTX 2000E Ada - ada_cuda434.149.9
RTX 2000E Ada - ada_cuda449.749.9
RTX 2000E Ada - ada_cuda45749.9
RTX 2000E Ada - ada_cuda472.749.9
RTX 2000E Ada - ada_cuda488.349.9
RTX 2000E Ada - ada_cuda496.750
RTX 2000E Ada - ada_cuda511.349.9
RTX 2000E Ada - ada_cuda519.649.9
RTX 2000E Ada - ada_cuda535.350
RTX 2000E Ada - ada_cuda542.649.9
RTX 2000E Ada - ada_cuda558.249.9
RTX 2000E Ada - ada_cuda565.549.9
RTX 2000E Ada - ada_cuda581.249.9
RTX 2000E Ada - ada_cuda589.550
RTX 2000E Ada - ada_cuda604.149.9
RTX 2000E Ada - ada_cuda612.550
RTX 2000E Ada - ada_cuda628.149.9
RTX 2000E Ada - ada_cuda635.450
RTX 2000E Ada - ada_cuda651.149.9
RTX 2000E Ada - ada_cuda658.449.9
RTX 2000E Ada - ada_cuda674.149.9
RTX 2000E Ada - ada_cuda682.449.9
RTX 2000E Ada - ada_cuda69749.9
Caveatms01: RAM runs at 4800 MT/s, rated 5600 MT/s (2 x 32 GB DDR5). Memory bandwidth and CPU-side LLM numbers are measured at the configured speed, not the rated one.

Samples are thinned to about 90 points for the chart; the full 1 second series is in the run's samples file.

Thinned further to 60 points for the article page; every kept point is an original sample.

During that run, Llama 3.1 8B generation settled at 33.4 tok/s, against 42.3 tok/s in the short run. So a long session on this card is slower than a quick benchmark suggests, and at 79 °C there is little thermal headroom in a small chassis. We did not measure fan noise.

Efficiency is respectable. On gpt-oss-20b the whole machine drew 96.7 W at the wall in the ada_cuda run, which is 0.633 tok/s per watt; the default run drew 147.3 W for 0.437 tok/s per watt, and we cannot explain that gap. On Llama 3.1 8B the figure is 0.396 tok/s per watt, close to the Ryzen AI Max+ 395's 0.393.

The Arc iGPU comparison

The igpu_arc configuration did not produce llama.cpp results, so there is no LLM comparison with the Arc iGPU. Its whisper result is 16.1x in the CUDA variant, which shows the NVIDIA card was still active, so we would not use that run to judge the iGPU. Its encoder numbers, above, are genuine.

Verdict

The RTX 2000E Ada is a good fit for a specific job: running 8B to 20B models at conversational speed, transcribing audio quickly and rendering with OptiX, inside a 50 W budget in a compact machine. It is not a route to 30B-class or larger models; memory, not speed, is the wall. If you want those, you need more memory, not a faster 16 GB card. Price and noise were not measured, so factor those in yourself.

The card can be swapped in the MS-02 Ultra, so you are not locked into it. We tested it in this machine.

The numbers

Specifications
Memory16,380 MiB (16 GB class), driver 595.99.02
Power50 W limit; 49 W average in the sustained run
Peak temperature79 °C
Llama 3.1 8B42.2 tok/s generation, 1,849 tok/s prompt (default run)
Qwen3 14B22.7 tok/s generation, 954 tok/s prompt (default run)
gpt-oss-20b64.3 tok/s generation, 1,625 tok/s prompt (default); 61.2 and 1,957 tok/s (ada_cuda)
Whisper large-v3-turbo15.2x real time (default), 16.0x (ada_cuda)
Blender BMW2726.9 s CUDA, 13.0 s OptiX
NVENC371 fps HEVC, 322 fps H.264, 393 fps AV1

Some links below may earn us a commission at no cost to you. See our affiliate disclosure.

What we left out

Price, noise, warranty and availability. We also did not test other cards, so we make no claims about the RTX 2000E Ada against its rivals.