Can Desktop PC · Radeon AI PRO R9700 · 32 GB RAM run gpt-oss-20b?
32 GB VRAM + 32 GB RAM · 640 GB/s memory bandwidth · gpt-oss-20b has 20.9B parameters (3.6B active per token).
Short answer
Yes, excellent for chat and comfortable or better for every workload we test.
Best quantization for chat: MXFP4 (11 GB of weights) on Lemonade. Generation: 170–230 tok/s, leaving about 19 GB free for your other apps.
How it rates for each workload
Same model and machine, different jobs. Agents and long documents send far bigger prompts than chat, so they need much more speed and memory.
| Workload | Verdict | Quant | Generation | First reply | Context | |
|---|---|---|---|---|---|---|
| Chatwith Open WebUI | Excellent | MXFP4 | 170–230 tok/s | under 1 s | 8K | Details |
| Coding questionswith Continue | Excellent | MXFP4 | 160–220 tok/s | ≈1 s | 16K | Details |
| Coding in a repositorywith Aider | Comfortable | MXFP4 | 140–190 tok/s | ≈3 s | 32K | Details |
| Agentic codingwith OpenCode | Comfortable | MXFP4 | 140–190 tok/s | ≈4 s | 32K | Details |
| Long documents (64K)with Open WebUI | Excellent | MXFP4 | 110–140 tok/s | ≈15 s | 64K | Details |
Speeds are estimates calibrated against measured benchmarks on similar hardware. “First reply” is the time to read the workload’s opening prompt. How we calculate
Get it running
Copy-paste commands for the MXFP4 build with a 64K context. Ollama and llama.cpp download the file straight from Hugging Face.
ollama run hf.co/unsloth/gpt-oss-20b-GGUF:F16
Downloads 13.79 GB (F16). Ollama's default context is small: set OLLAMA_CONTEXT_LENGTH=65536 before `ollama serve` for long prompts.
Other models for Desktop PC · Radeon AI PRO R9700 · 32 GB RAM
The best-rated models for chat on this machine.
- Qwen3.6 35B-A3B160–220 tok/sExcellent
- Gemma 4 26B-A4B110–150 tok/sExcellent
- LFM2.5 24B-A2B280–380 tok/sExcellent
- Qwen3.5 35B-A3B160–220 tok/sExcellent
- GLM-4.7-Flash (30B-A3B)140–180 tok/sExcellent
- Qwen3 30B-A3B Instruct 2507120–160 tok/sExcellent
Cheapest machines for gpt-oss-20b
Hardware rated comfortable or better for chat, lowest price first.
- Mac mini M4 24 GB$999 · 25–35 tok/sExcellent
- Mac mini M6 24 GB$1,299 · 30–50 tok/sExcellent
- Laptop · Ryzen AI 9 HX 370 (Radeon 890M) · 32 GB$1,300 · 20–35 tok/sExcellent
- Laptop · Core Ultra 7 258V (Arc 140V) · 32 GB$1,300 · 18–30 tok/sExcellent
- Desktop PC · GeForce RTX 5060 Ti 16GB · 32 GB RAM$1,330 · ≈100 tok/sExcellent
- Desktop PC · GeForce RTX 4060 Ti 16GB · 32 GB RAM$1,350 · 50–85 tok/sExcellent
Same chip, other memory: 64 GB
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.