Can I Run GPT-OSS 20B on NVIDIA GeForce RTX 3070?
Autor: Jakub Rusinowski · Ostatnia aktualizacja: 15 sierpnia 2026
Not at MXFP4 — that needs 12.1 GB at 8K context and the NVIDIA GeForce RTX 3070 has 8 GB. Drop to Q2_K and it fits in 7.9 GB, with up to 8K of context.
Get a personalized upgrade path →
The numbers
| Model | GPT-OSS 20B |
| Parameters | 20B |
| Quantization | MXFP4 |
| VRAM needed (8K context) | 12.1 GB |
| NVIDIA GeForce RTX 3070 VRAM | 8 GB |
| Verdict | Runs at a lower quant |
| Fits at | Q2_K (7.9 GB) |
| Max context | 8K |
GPT-OSS 20B on the NVIDIA GeForce RTX 3070: VRAM by quantization
| Quant | VRAM needed | Fits 8 GB? | Max context | Whole PC |
|---|---|---|---|---|
| F16 | 42.8 GB | ✗ No | — | — |
| Q8_0 | 23.2 GB | ✗ No | — | — |
| Q6_K | 18.2 GB | ✗ No | — | — |
| Q5_K_M | 15.8 GB | ✗ No | — | — |
| Q4_K_M | 13.6 GB | ✗ No | — | — |
| Q3_K_M | 9.9 GB | ✗ No | — | — |
| Q2_K | 7.9 GB | ✓ Yes | 8K | — |
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 8 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 MXFP4 on the NVIDIA GeForce RTX 3070: 8K 12.1 GB ✗ · 32K 12.7 GB ✗ · 128K 15.1 GB ✗. Past 8K it no longer fits 8 GB — a q8_0 KV cache buys roughly half of that back, which the calculator will price for you.
What to do next
Quantize to Q2_K. That is the cheapest fix — it costs some quality but no money.
No compatible GPU? GPT-OSS 20B on 16 GB of system RAM, CPU only: runs.
Running GPT-OSS 20B on this card:
GPT-OSS 20B needs ~12 GB but this GPU has 8 GB. Rent a RTX 4090 (24 GB)-class GPU by the hour instead of buying one:
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 GeForce RTX 3070
- GPT-OSS 120B — does not fit (71.6 GB)
GPT-OSS 20B on nearby hardware
- NVIDIA GeForce RTX 3080 (10GB) (10 GB) — runs at a lower quant
All GPT-OSS sizes on the NVIDIA GeForce RTX 3070 | GPT-OSS 20B model page | NVIDIA GeForce RTX 3070 GPU page | VRAM calculator | Check your hardware