Hardware / NVIDIA
Can an NVIDIA GB10 run Llama 3.1 405B?
NVIDIA GB10 has 128 GB unified memory. About 89.6 GB is treated as usable. Grace Blackwell Superchip as reported with 128 GB unified memory. Multi-node rows are separate. The title asks about Llama 3.1 405B because it is the largest catalog model still in range of this memory.
Manufacturer page for NVIDIA GB10
Compatibility
| Model | Q4 | Q8 | FP16 | MXFP4 |
|---|---|---|---|---|
| gpt-oss 120B gpt-oss · 117B stored · 5.1B active | 71.6 GB Fits estimate No measured run | 125 GB Tight estimate No measured run | 234 GB Over estimate No measured run | 61.5 GB Fits checkpoint No measured run |
| Llama 3 70B Llama · 70B stored | 45.7 GB Fits estimate · KV at 8k No measured run | 77.6 GB Fits estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| Llama 3.1 70B Llama · 70B stored | 45.7 GB Fits estimate · KV at 8k No measured run | 77.6 GB Fits estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| Llama 3.3 70B Llama · 70B stored | 45.7 GB Fits estimate · KV at 8k No measured run | 77.6 GB Fits estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| DeepSeek R1 Distill 70B DeepSeek · 70B stored | 45.7 GB Fits estimate · KV at 8k No measured run | 77.6 GB Fits estimate · KV at 8k No measured run | 143 GB Over estimate · KV at 8k No measured run | — |
| Qwen3.6 35B-A3B Qwen · 35B stored · 3B active | 22.1 GB Fits estimate · KV at 8k No measured run | 38.1 GB Fits estimate · KV at 8k No measured run | 70.9 GB Fits estimate · KV at 8k No measured run | — |
| Gemma 4 31B Gemma · 30.7B stored | 19.4 GB Fits estimate No measured run | 33.4 GB Fits estimate No measured run | 62.1 GB Fits estimate No measured run | — |
| Qwen3 30B-A3B Qwen · 30B stored · 3B active | 18.9 GB Fits estimate No measured run | 32.6 GB Fits estimate No measured run | 60.8 GB Fits estimate No measured run | — |
| Qwen3.8 27B Qwen · 27B stored | 17.6 GB Fits estimate · KV at 8k No measured run | 29.9 GB Fits estimate · KV at 8k No measured run | 55.3 GB Fits estimate · KV at 8k No measured run | — |
| Gemma 4 26B-A4B Gemma · 25.2B stored · 3.8B active | 16.0 GB Fits estimate No measured run | 27.5 GB Fits estimate No measured run | 51.1 GB Fits estimate No measured run | — |
| gpt-oss 20B gpt-oss · 20.9B stored · 3.6B active | 13.4 GB Fits estimate No measured run | 23.0 GB Fits estimate No measured run | 42.6 GB Fits estimate No measured run | 13.6 GB Fits checkpoint No measured run |
| Qwen3 14B Qwen · 14B stored | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run | — |
| DeepSeek R1 Distill 14B DeepSeek · 14B stored | 9.2 GB Fits estimate No measured run | 15.6 GB Fits estimate No measured run | 28.8 GB Fits estimate No measured run | — |
| Gemma 3 12B Gemma · 12B stored | 8.0 GB Fits estimate No measured run | 13.5 GB Fits estimate No measured run | 24.8 GB Fits estimate No measured run | — |
| Gemma 4 12B Gemma · 12B stored | 8.0 GB Fits estimate No measured run | 13.4 GB Fits estimate No measured run | 24.6 GB Fits estimate No measured run | — |
| Llama 3 8B Llama · 8B stored | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | — |
| Llama 3.1 8B Llama · 8B stored | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | — |
| Qwen3 8B Qwen · 8B stored | 5.6 GB Fits estimate No measured run | 9.3 GB Fits estimate No measured run | 16.8 GB Fits estimate No measured run | — |
| Gemma 4 E4B Gemma · 8B stored | 5.6 GB Fits estimate No measured run | 9.3 GB Fits estimate No measured run | 16.8 GB Fits estimate No measured run | — |
| DeepSeek R1 Distill 8B DeepSeek · 8B stored | 6.6 GB Fits estimate · KV at 8k No measured run | 10.3 GB Fits estimate · KV at 8k No measured run | 17.8 GB Fits estimate · KV at 8k No measured run | — |
| Llama 2 7B Llama · 7B stored | 9.0 GB Fits estimate · KV at 8k No measured run | 12.2 GB Fits estimate · KV at 8k No measured run | 18.8 GB Fits estimate · KV at 8k No measured run | — |
| Llama 3.2 3B Llama · 3B stored | 3.4 GB Fits estimate · KV at 8k No measured run | 4.8 GB Fits estimate · KV at 8k No measured run | 7.6 GB Fits estimate · KV at 8k No measured run | — |
| DeepSeek R1 671B DeepSeek · 671B stored · 37B active | 408 GB Over estimate No measured run | 714 GB Over estimate No measured run | 1343 GB Over estimate No measured run | — |
| Llama 3.1 405B Llama · 405B stored | 250 GB Over estimate · KV at 8k No measured run | 435 GB Over estimate · KV at 8k No measured run | 815 GB Over estimate · KV at 8k No measured run | — |
| Qwen3 235B-A22B Qwen · 235B stored · 22B active | 143 GB Over estimate No measured run | 250 GB Over estimate No measured run | 471 GB Over estimate No measured run | — |
Measured runs on this device
- Qwen3.6 35B-A3B · NVFP4 · 113 tok/s · speculative · vLLM 0.30 + MTP source
- Qwen3.6 35B-A3B · NVFP4 + MTP (k=2) · 102.3 tok/s · speculative · vLLM 0.31.0, 128K ctx, 1 user source
- gpt-oss 20B · not stated · 96.2 tok/s · vLLM 0.31.0, 128K ctx, 1 user source
- Qwen3.6 35B-A3B · NVFP4 + MTP · 95.1 tok/s · speculative · vLLM, 1 stream source
- Qwen3.6 35B-A3B · NVFP4 · 86 tok/s · speculative · vLLM 0.30 + MTP source
- Qwen3.6 35B-A3B · NVFP4, no speculative decoding · 78.1 tok/s · vLLM 0.31.0, 128K ctx, 1 user source
- Qwen3.8 27B · MLX 4-bit + DFlash2 · 58.3 tok/s · speculative · TensorFold, 1 stream source
- Gemma 4 26B-A4B · + official MTP drafter (k=3) · 56.5 tok/s · speculative · vLLM 0.31.0, 128K ctx, 1 user source
- gpt-oss 120B · not stated · 44.4 tok/s · vLLM 0.31.0, 128K ctx, 1 user source
- Gemma 4 26B-A4B · no speculative decoding · 30.8 tok/s · vLLM 0.31.0, 128K ctx, 1 user source
- Qwen3.8 27B · NVFP4 (Unsloth, 4-bit, 23.4 GB on disk) · 26.7 tok/s · speculative · vLLM 0.1.dev20003, MTP n=3, FP8 KV, 351K context source
- Llama 3.1 8B · not stated · 26.4 tok/s · NVIDIA NIM 2.0.9, 128K ctx, 1 user source
- Qwen3.8 27B · + MTP (k=2) · 19.0 tok/s · speculative · vLLM 0.31.0, 128K ctx, 1 user source
- Qwen3.8 27B · NVFP4 + DSpark · 18.3 tok/s · speculative · SGLang, 1 stream source
- Qwen3.8 27B · no speculative decoding · 11.0 tok/s · vLLM 0.31.0, 128K ctx, 1 user source