Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
129.6 tok/s
TTFT
1494 ms
Safe context
22K
Memory
17.2 GB / 24.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | B | Runs well | 136.8 tok/s | 2058 ms | 44K |
| Chat | B | Runs well | 136.8 tok/s | 772 ms | 11K |
| Coding | B | Runs well | 129.6 tok/s | 1494 ms | 22K |
| RAG | B | Runs well | 136.8 tok/s | 2573 ms | 44K |
| Reasoning | B | Runs well | 136.8 tok/s | 1672 ms | 22K |
How GPT-OSS 20B (21B params) fits at each quantization level on RTX 4090 24GB (24.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 8.2 GB | Low | D37 |
Q3_K_S | 3 | 10.3 GB | Low | D38 |
NVFP4 | 4 |
ollama run gpt-oss-20bhuggingface-cli download gpt-oss-20b11.8 GB |
| Medium |
| D40 |
Q4_K_M | 4 | 12.8 GB | Medium | C41 |
Q5_K_M | 5 | 15.1 GB | High | C43 |
Q6_KBest for your GPU | 6 | 17.2 GB | High | C44 |
Q8_0 | 8 | 22.5 GB | Very High | C44 |
F16 | 16 | 43.1 GB | Maximum | F0 |