Can I Run GPT-OSS 120B on NVIDIA RTX PRO 6000 Blackwell?
Written by Jakub Rusinowski · Last updated July 21, 2026
Yes. GPT-OSS 120B needs 71.9 GB at 8K context (70.5 GB weights + 1.4 GB KV cache/overhead) at Q4_K_M and the NVIDIA RTX PRO 6000 Blackwell has 96 GB, leaving about 24.1 GB of headroom, at roughly 224 tok/s (estimated) with room for up to 128K of context.
See what else this hardware can run →
The numbers
| Model | GPT-OSS 120B |
| Parameters | 120B |
| Quantization | Q4_K_M |
| VRAM needed (8K context) | 71.9 GB |
| NVIDIA RTX PRO 6000 Blackwell VRAM | 96 GB |
| Verdict | Runs |
| Max context | 128K |
| Estimated speed | ~224 tok/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 | 235 GB | ✗ No | — | — |
| Q8_0 | 125.5 GB | ✗ No | — | — |
| Q6_K | 97.2 GB | ✗ No | — | — |
| Q5_K_M | 84.2 GB | ✓ Yes | 128K | — |
| Q4_K_M | 71.9 GB | ✓ Yes | 128K | — |
| Q3_K_M | 51.2 GB | ✓ Yes | 128K | — |
| Q2_K | 39.8 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 71.9 GB · 32K 73.7 GB · 128K 81 GB. Every window this model publishes still fits 96 GB.
What to do next
Nothing to change — run it at Q4_K_M. If you want more capability, check whether the next size up also fits.
No compatible GPU? GPT-OSS 120B on 96 GB of system RAM, CPU only: runs, but it is tight.
Running GPT-OSS 120B on this card:
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.
Other GPT-OSS sizes on the NVIDIA RTX PRO 6000 Blackwell
- GPT-OSS 20B — runs (12.3 GB)
GPT-OSS 120B on nearby hardware
- NVIDIA H100 80GB (PCIe) (80 GB) — runs
- Apple M4 Max (128 GB) — runs
All GPT-OSS sizes on the NVIDIA RTX PRO 6000 Blackwell | GPT-OSS 120B model page | NVIDIA RTX PRO 6000 Blackwell GPU page | VRAM calculator | Check your hardware