Can the Radeon RX 9070 XT Run gpt-oss-20b?
Runs
Yes. gpt-oss-20b at MXFP4 is a 12.1 GB download (Hugging Face file listing for ggml-org/gpt-oss-20b-GGUF), and the Radeon RX 9070 XT has 16 GB of VRAM, leaving about 3.9 GB for the KV cache and runtime. Published runs put generation at a median of 91.9 tokens per second across 1 cited measurement. Fastest cited run: GitHub hirokuze/local-llm-benchmark-rx9070xt.
Buy the Radeon RX 9070 XT
PowerColor Hellhound Spectral White AMD Radeon RX 9070 XT 16GB GDDR6Tracked at $799 on 2026-08-28 — price may vary.
Published runs for gpt-oss-20b on the Radeon RX 9070 XT
| Generation | Quant | Runtime | Context | Source | Date |
|---|---|---|---|---|---|
| 91.9 tok/s | Q4_K_M | ollama | — | GitHub hirokuze/local-llm-benchmark-rx9070xtlabelled "gpt-oss:20b" | 2026-04-01 |
More about this pair
How much VRAM does gpt-oss-20b need?
The MXFP4 file is 12.1 GB. Add roughly 1.5 GB for the runtime and an ~8K-token context, so about 13.6 GB of VRAM holds it comfortably. Longer contexts grow the KV cache and need more.
What is the fastest gpt-oss-20b can generate on the Radeon RX 9070 XT?
gpt-oss-20b is a mixture-of-experts model that reads about 2.1 GB of active weights per token. At the Radeon RX 9070 XT's 645 GB/s of memory bandwidth, that sets a ceiling near 310 tokens per second. Real runs land below it.
Check another pair
gpt-oss-20b on other GPUs
- RTX 4060 — Offload
- RTX 3060 Ti — Offload
- RTX 3060 12GB — Offload
- Intel Arc B580 — Offload
- RTX 4070 SUPER — Offload
- RTX 4060 Ti 16GB — Runs
- RTX 5060 Ti 16GB — Runs
- Intel Arc A770 16GB — Runs
- RTX 4070 Ti SUPER — Runs, 98.7 tok/s median
- RTX 4080 — Runs, 138 tok/s median
- RTX 5070 Ti — Runs
- RTX 5080 — Runs, 134 tok/s median
- RTX 3090 — Runs
- Radeon RX 7900 XTX — Runs
- RTX 4090 — Runs
- RTX 5090 — Runs
- RTX A6000 48GB — Runs
- RTX PRO 6000 Blackwell 96GB — Runs
Other models on the Radeon RX 9070 XT
- Llama 3.2 1B — Runs
- Llama 3.2 3B — Runs
- Mistral 7B — Runs
- Qwen2.5 7B — Runs
- Llama 3.1 8B — Runs
- DeepSeek-R1-Distill-Llama 8B — Runs
- Qwen3 8B — Runs, 90 tok/s median
- Gemma 2 9B — Runs
- Gemma 3 12B — Runs
- Qwen2.5 14B — Runs
- DeepSeek-R1-Distill-Qwen 14B — Runs
- Qwen3 14B — Runs, 50.1 tok/s median
- Phi-4 14B — Runs
- Gemma 3 27B — Offload
- Gemma 2 27B — Offload
- Qwen3 30B-A3B — Offload
- Qwen3 32B — Offload
- Qwen2.5 32B — Offload
- DeepSeek-R1-Distill-Qwen 32B — Offload
- Llama 3.1 70B — Offload
- Llama 3.3 70B — Offload
- DeepSeek-R1-Distill-Llama 70B — Offload
How the checks work
The fit is the MXFP4 file size against the card's VRAM, with 1.5 GB kept for the runtime and an ~8K context. A published run counts only if the pair fits, the run is Q4-class, its source does not call it an estimate, it is under the bandwidth ceiling above, and it is not one figure pasted across many cards. The whole matrix is downloadable as a CSV under CC BY 4.0.
As an Amazon Associate, SpecPicks earns from qualifying purchases.
This page is editorial synthesis based on publicly available information. No independent first-party benchmarking is reported.