Can I Run GPT-OSS on NVIDIA RTX PRO 6000 Blackwell?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
Yes, comfortably — GPT-OSS 120B at Q4_K_M needs 71.6 GB at 8K context (70.5 GB weights + 1.1 GB KV cache/overhead), leaving ~24.4 GB of the NVIDIA RTX PRO 6000 Blackwell's 96 GB, at ~228 tok/s (est.), with room for up to 128K context.
See what else this hardware can run →
lub porównaj w Vast.ai od $0.77/godz. (typical low · varies)
Jako partner Amazon zarabiamy na kwalifikujących się zakupach. Linki do chmurowych GPU są linkami polecającymi — możemy otrzymać prowizję bez dodatkowych kosztów dla Ciebie.
NVIDIA RTX PRO 6000 Blackwell Specs
| VRAM | 96 GB |
| Memory Bandwidth | 1792 GB/s |
GPT-OSS 120B on the NVIDIA RTX PRO 6000 Blackwell: VRAM by quantization
| Quant | VRAM needed | Fits 96 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 234.7 GB | ✗ No | — | — |
| Q8_0 | 125.2 GB | ✗ No | — | — |
| Q6_K | 96.9 GB | ✗ No | — | — |
| Q5_K_M | 83.9 GB | ✓ Yes | 128K | — |
| Q4_K_M | 71.6 GB | ✓ Yes | 128K | — |
| Q3_K_M | 50.9 GB | ✓ Yes | 128K | — |
| Q2_K | 39.5 GB | ✓ Yes | 128K | — |
Assumes an 8K-token context with an f16 KV cache. A longer window needs more; a quantized KV cache needs less. “Max context” is the largest window that still fits in 96 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
Context costs VRAM too. At Q4_K_M on the NVIDIA RTX PRO 6000 Blackwell: 8K 71.6 GB · 32K 72.6 GB · 128K 76.2 GB. Every window this model publishes still fits 96 GB.
No compatible GPU? GPT-OSS 120B on 96 GB of system RAM, CPU only: runs, but it is tight.
GPT-OSS Sizes That Fit the NVIDIA RTX PRO 6000 Blackwell (at 8K context)
| GPT-OSS 120B | Q4_K_M · 71.6 GB at 8K context · ~228 tok/s (est.) |
| GPT-OSS 20B | MXFP4 · 12.1 GB at 8K context · ~279 tok/s (est.) |
At 2 hrs/day, buying (~$8,565) beats renting at $0.77/hr after about 15.4 years.
Affiliate links — we may earn a commission if you sign up, at no extra cost to you.
Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.
FAQ
Is the NVIDIA RTX PRO 6000 Blackwell enough to run GPT-OSS locally?
Yes, comfortably — GPT-OSS 120B at Q4_K_M needs 71.6 GB at 8K context (70.5 GB weights + 1.1 GB KV cache/overhead), leaving ~24.4 GB of the NVIDIA RTX PRO 6000 Blackwell's 96 GB, at ~228 tok/s (est.), with room for up to 128K context.
What's the best GPT-OSS size for the NVIDIA RTX PRO 6000 Blackwell?
GPT-OSS 120B at Q4_K_M quantization needs 71.6 GB at 8K context (70.5 GB weights + 1.1 GB KV cache/overhead), estimated ~228 tokens/sec, up to 128K context.
Every GPT-OSS size on the NVIDIA RTX PRO 6000 Blackwell
| Size | VRAM at 8K | Verdict | Speed |
|---|---|---|---|
| GPT-OSS 120B | 71.6 GB | Runs | ~228 tok/s |
| GPT-OSS 20B | 12.1 GB | Runs | ~279 tok/s |
GPT-OSS on Other GPUs
- GPT-OSS on Apple M2 Max
- GPT-OSS on NVIDIA A100 80GB (PCIe)
- GPT-OSS on NVIDIA H100 80GB (PCIe)
- GPT-OSS on Apple M4 Max
Popular Models on the NVIDIA RTX PRO 6000 Blackwell
VRAM Tier
Troubleshooting
Buying Guide
← Can I Run It? | GPT-OSS Model Page | NVIDIA RTX PRO 6000 Blackwell GPU Page | VRAM calculator | Check Your Hardware