Written by Jakub Rusinowski · Last updated August 15, 2026
Yes, but it's tight — GPT-oss 120B at Q4_K_M needs 72.45 GB of the NVIDIA H100 80GB's 80 GB, leaving only ~7.5 GB, ~22 tok/s (est.) with room for up to 64K context.
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
| VRAM | 80 GB |
| Memory Bandwidth | 2000 GB/s |
| Quant | VRAM needed | Fits 80 GB? | Max context |
|---|---|---|---|
| F16 | 241.1 GB | ✗ No | — |
| Q8_0 | 128.6 GB | ✗ No | — |
| Q6_K | 99.5 GB | ✗ No | — |
| Q5_K_M | 86.2 GB | ✗ No | — |
| Q4_K_M | 73.6 GB | ✓ Yes | 64K |
| Q3_K_M | 52.3 GB | ✓ Yes | 64K |
| Q2_K | 40.6 GB | ✓ Yes | 64K |
VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 80 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
| GPT-oss 120B | Q4_K_M · 72.45 GB · ~22 tok/s (est.) |
| GPT-OSS 20B | MXFP4 · 10.625 GB · ~116 tok/s (est.) |
At 2 hrs/day, buying (~$25,000) beats renting at $0.77/hr after about 45.1 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.
Yes, but it's tight — GPT-oss 120B at Q4_K_M needs 72.45 GB of the NVIDIA H100 80GB's 80 GB, leaving only ~7.5 GB, ~22 tok/s (est.) with room for up to 64K context.
GPT-oss 120B at Q4_K_M quantization (72.45 GB), estimated ~22 tokens/sec, up to 64K context.
← Can I Run It? | GPT-OSS Model Page | NVIDIA H100 80GB GPU Page | Check Your Hardware