ASUS Ascent GX10 vs Dell Pro Max GB10
Ascent GX10 · NVIDIA GB10 · 128 GB unified and Dell Pro Max with GB10 (FCM1253) · NVIDIA GB10 · 128 GB unified side by side for local AI.
Facts from both hardware pages
| Specification | ASUS Ascent GX10 | Dell Pro Max GB10 |
|---|---|---|
| Memory | 128 GB unified memoryShared by CPU and GPU · source | 128 GB unified memoryShared by CPU and GPU · source |
| Memory bandwidth | 273 GB/sManufacturer spec · not model speed · source | 273 GB/sManufacturer spec · not model speed · source |
| Text · run well | 193+1 tight fit · within 128 GB | 193+1 tight fit · within 128 GB |
| Vision · run well | 150within 128 GB | 150within 128 GB |
| Image · within memory | 77within 128 GB · documented paths and minimums | 77within 128 GB · documented paths and minimums |
| Video · within memory | 73within 128 GB · documented paths and minimums | 73within 128 GB · documented paths and minimums |
| Audio · within memory | 134within 128 GB · documented paths and minimums | 134within 128 GB · documented paths and minimums |
| Embeddings · within memory | 91within 128 GB · 8-bit estimate | 91within 128 GB · 8-bit estimate |
| Published speed runs | 11 naming only the chip · +13 same-chip references | 11 naming only the chip · +13 same-chip references |
| Launch price (MSRP) | USD 5,999US · manufacturer store, read 2026-10-18 · not a tracked offer · source | USD 5,903US · manufacturer store, read 2026-10-18 · not a tracked offer · source |
| Where to buy | ASUS Storechoose the configuration there · US · recorded 2026-10-18 · store link | Dell.comchoose the configuration there · US · recorded 2026-10-18 · store link |
Counts use the same memory estimate as each hardware page: text and vision run well within the fast memory (tight fits counted apart); image, video and audio use documented paths and publisher minimums. Formulas
Top text models each runs well
The first 5 rows of each hardware page's Text list, in its order: LiveBench score, then reviewed models, then Hub downloads. Memory is the planning estimate on that machine.
| Rank | ASUS Ascent GX10 | Dell Pro Max GB10 |
|---|---|---|
| #1 | Smaug MiniAbacus AI · LiveBench 76.9 · ~29 GB | Smaug MiniAbacus AI · LiveBench 76.9 · ~29 GB |
| #2 | Qwen3.8 27BAlibaba · LiveBench 75.3 · ~29 GB | Qwen3.8 27BAlibaba · LiveBench 75.3 · ~29 GB |
| #3 | Qwen3.6 27BAlibaba · LiveBench 64 · ~29 GB | Qwen3.6 27BAlibaba · LiveBench 64 · ~29 GB |
| #4 | Qwen3 14BAlibaba · ~20 GB | Qwen3 14BAlibaba · ~20 GB |
| #5 | Gemma 4 31BGoogle · ~32 GB | Gemma 4 31BGoogle · ~32 GB |
Measured speed
Published output tokens per second, as measured. A speed is compared only when the same checkpoint, quantization, runtime and lengths ran on both machines themselves; same-chip references are not compared.
The Llama 2 7B Q4_0 result names only the chip (Nvidia GB10), so it appears on both pages and is not compared. No other published test ran on both.
All published measurements · ASUS Ascent GX10
| gpt-oss 20B MXFP4 MoE | 83.43 ± 0.59 | MXFP4 MoE | CUDA | llama.cpp bench |
|---|---|---|---|---|
| gemma-3-4b-it-qat Q4_0 | 81.05 ± 0.20 | Q4_0 | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Qwen3.5 35B A3B MXFP4 | 63.13 | MXFP4 (MoE; 35B total / 3B active) | llama.cpp CUDA (SM121a, source build) | nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark |
| Qwen3 Coder 30B A3B Q8_0 | 61.06 ± 0.23 | Q8_0 | CUDA | llama.cpp bench |
| Llama 2 7B Q4_0 | 60.39 ± 0.05 | Q4_0 | Vulkan | llama.cpp Vulkan scoreboard · community result |
| gpt-oss-120b MXFP4 MoE | 58.72 ± 0.20 | MXFP4 MoE | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Nemotron-3-Nano-4B Q8_0 | 52.85 ± 0.12 | Q8_0 | llama.cpp CUDA | llama.cpp benches/nemotron · maintainer result |
| GLM-4.7-Flash Q8_0 | 48.68 ± 0.12 | Q8_0 | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Qwen3.8 27B NVFP4 + DSpark | 36.6 | NVFP4 + DSpark | SGLang | NVIDIA Developer Forum |
| Qwen2.5-Coder-7B-Q8_0 | 29.43 ± 0.02 | Q8_0 | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Nemotron 3 Super 120B A12B Q4_K | 19.94 ± 0.16 | Q4_K (reported as 'Q4_K' by llama-bench; GGUF from ggml-org) | llama.cpp CUDA | llama.cpp benches/nemotron · DGX Spark |
| Qwen3.8 27B NVFP4 + MTP | 18.5 | NVFP4 + MTP (3 speculative tokens) | vLLM official | NVIDIA Developer Forum |
| Qwen3.6 27B Q4_K_M | 11.85 ± 0.01 | Q4_K_M (15.65 GiB) | llama.cpp CUDA (SM121a, source build) | nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark |
| Qwen3.6 27B BF16 | 4.54 ± 0.00 | BF16 (50.10 GiB) | llama.cpp CUDA (SM121a, source build) | nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark |
All published measurements · Dell Pro Max GB10
| gpt-oss 20B MXFP4 MoE | 83.43 ± 0.59 | MXFP4 MoE | CUDA | llama.cpp bench |
|---|---|---|---|---|
| gemma-3-4b-it-qat Q4_0 | 81.05 ± 0.20 | Q4_0 | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Qwen3.5 35B A3B MXFP4 | 63.13 | MXFP4 (MoE; 35B total / 3B active) | llama.cpp CUDA (SM121a, source build) | nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark |
| Qwen3 Coder 30B A3B Q8_0 | 61.06 ± 0.23 | Q8_0 | CUDA | llama.cpp bench |
| Llama 2 7B Q4_0 | 60.39 ± 0.05 | Q4_0 | Vulkan | llama.cpp Vulkan scoreboard · community result |
| gpt-oss-120b MXFP4 MoE | 58.72 ± 0.20 | MXFP4 MoE | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Nemotron-3-Nano-4B Q8_0 | 52.85 ± 0.12 | Q8_0 | llama.cpp CUDA | llama.cpp benches/nemotron · maintainer result |
| GLM-4.7-Flash Q8_0 | 48.68 ± 0.12 | Q8_0 | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Qwen3.8 27B NVFP4 + DSpark | 36.6 | NVFP4 + DSpark | SGLang | NVIDIA Developer Forum |
| Qwen2.5-Coder-7B-Q8_0 | 29.43 ± 0.02 | Q8_0 | llama.cpp CUDA | llama.cpp benches/dgx-spark · maintainer result |
| Nemotron 3 Super 120B A12B Q4_K | 19.94 ± 0.16 | Q4_K (reported as 'Q4_K' by llama-bench; GGUF from ggml-org) | llama.cpp CUDA | llama.cpp benches/nemotron · DGX Spark |
| Qwen3.8 27B NVFP4 + MTP | 18.5 | NVFP4 + MTP (3 speculative tokens) | vLLM official | NVIDIA Developer Forum |
| Qwen3.6 27B Q4_K_M | 11.85 ± 0.01 | Q4_K_M (15.65 GiB) | llama.cpp CUDA (SM121a, source build) | nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark |
| Qwen3.6 27B BF16 | 4.54 ± 0.00 | BF16 (50.10 GiB) | llama.cpp CUDA (SM121a, source build) | nabe2030/dense-27b-31b-dgx-spark (GitHub) · community benchmark |
Verdict
Both have 128 GB unified memory. By the memory estimate, 193 text models run well on each. Both list 273 GB/s of memory bandwidth. The published Llama 2 7B Q4_0 run (Vulkan) names only the chip, not the machine, so both pages show the same result; it does not tell them apart. Launch prices on file: ASUS Ascent GX10 USD 5,999 (2026-10-18) and Dell Pro Max GB10 USD 5,903 (2026-10-18). Same chip and memory: the estimate gives both the same model lists, so the choice comes down to price, seller and the rest of the machine.
Limits and dates
Model counts are memory estimates, not speed measurements or guaranteed fits; verify runtime and checkpoint support. Bandwidth is the manufacturer's figure. Prices are launch or list prices with their dates, not current offers.
Page updated · Model catalog checked · LiveBench 2026-06-25