GPUFits
Can A100 80GB run gpt-oss-120b?
⚠️ Tight
gpt-oss-120b @ Q4_K_M · 8K context
Needed
73.6 GB
Usable
80.0 GB
VRAM breakdown
| Weights (Q4_K_M) | 71.5 GB |
| KV cache (8K context) | 0.6 GB |
| Runtime overhead | 1.5 GB |
| Total | 73.6 GB |
Computed at 8K context with fp16 KV cache. Longer contexts need more VRAM — use the VRAM calculator for other settings.
Recommended quantization
Q4_K_M
Estimated generation speed
~490 tok/s @ Q4_K_M
Theoretical estimates based on published architecture data and measured GGUF sizes; real-world speed varies ±30%.
Smaller models this GPU runs well
FAQ
- How much VRAM does gpt-oss-120b need?
- At Q4_K_M with 8K context: 71.5GB weights + 0.6GB KV cache + 1.5GB runtime overhead = 73.6GB total. A100 80GB offers 80.0GB usable VRAM, so the verdict is: Tight fit.
- What is the best quantization for gpt-oss-120b on A100 80GB?
- Q4_K_M — the highest tier that still fits within 80.0GB usable VRAM at 8K context. Lower tiers (Q3/Q2) fit too but cost noticeable quality.
- How fast does gpt-oss-120b run on A100 80GB?
- About 490 tokens/s at Q4_K_M (theoretical estimate, ±30% in real-world use).
Check another combination in the GPU Checker →
Data verified 2026-08-04