作者： Jakub Rusinowski · 最后更新： 2026年8月15日
Yes, comfortably — you'll have ~13.4 GB of headroom running GPT-OSS 20B at MXFP4 (10.625 GB, ~72 tok/s (est.)).
or compare on Vast.ai from $0.35/hr (typical low · varies)
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 | 24 GB |
| Memory Bandwidth | 1008 GB/s |
| Quant | VRAM needed | Fits 24 GB? | Max context |
|---|---|---|---|
| F16 | 41 GB | ✗ No | — |
| Q8_0 | 22.3 GB | ✓ Yes | 32K |
| Q6_K | 17.4 GB | ✓ Yes | 128K |
| Q5_K_M | 15.2 GB | ✓ Yes | 128K |
| Q4_K_M | 13.1 GB | ✓ Yes | 128K |
| Q3_K_M | 9.5 GB | ✓ Yes | 128K |
| Q2_K | 7.6 GB | ✓ Yes | 128K |
VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 24 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.
| GPT-OSS 20B | MXFP4 · 10.625 GB · ~72 tok/s (est.) |
At 2 hrs/day, buying (~$1,599) beats renting at $0.34/hr after about 6.5 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, comfortably — you'll have ~13.4 GB of headroom running GPT-OSS 20B at MXFP4 (10.625 GB, ~72 tok/s (est.)).
GPT-OSS 20B at MXFP4 quantization (10.625 GB), estimated ~72 tokens/sec.
| Size | VRAM | Verdict | Speed |
|---|---|---|---|
| GPT-oss 120B | 72.5 GB | Does not fit | — |
| GPT-OSS 20B | 10.6 GB | Runs | ~72 tok/s |
← Can I Run It? | GPT-OSS Model Page | NVIDIA GeForce RTX 4090 GPU Page | Check Your Hardware