Model benchmarks
unsloth/gpt-oss-20b-GGUF local LLM performance
As of September 2026, unsloth/gpt-oss-20b-GGUF runs at up to 23.0 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
20B
Peak speed
23.0 tok/s
Average speed
21.7 tok/s
Avg PP
206.0 tok/s
Min memory
9.8 GB
Max context
16.384 tokens
Avg output / run
20.991 tokens
Avg runtime / run
17m 18s
Avg quality
49.4
Benchmark runs
3
GPUs tested
1
Quality by task
Average LLM-judged quality (0–100) with the run-to-run spread shown as a P5–P95 band, overall and for each benchmark task, across all 3 runs. The low and high columns show how much the judge’s score varies between runs, and need at least two runs to display.
| Task | P5 (low) | Avg | P95 (high) |
|---|---|---|---|
| Overall | 31.4 | 49.4 | 60.6 |
| Agent Workflow | 8.9 | 60.2 | 91.1 |
| Code Generation | 0.0 | 2.1 | 5.6 |
| Role Play & Narrative | 62.0 | 66.4 | 73.4 |
| Research & Analysis | 37.9 | 69.0 | 88.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination unsloth/gpt-oss-20b-GGUF has been benchmarked on, ranked by peak token generation speed. Last updated September 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Intel(R) Arc(TM) 140V GPU (16GB) | llama.cpp | — | 23.0 tok/s | 21.7 tok/s | 9.8 GB | 16.384 tokens | 49.4 | 3 |
Benchmark runs
All 3 unsloth/gpt-oss-20b-GGUF runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is unsloth/gpt-oss-20b-GGUF good for coding?
- In our benchmarks, unsloth/gpt-oss-20b-GGUF scores 2.1/100 for coding. It runs at about 21.7 tok/s, so if you want more speed, /home/polaris/models/Tiel-Coder-35B-A3B-MTP-UD-Q6_K_XL.gguf is faster (~35.6 tok/s) and still scores well for coding (84.9/100).
- Is unsloth/gpt-oss-20b-GGUF good for agentic (tool-using) tasks?
- In our benchmarks, unsloth/gpt-oss-20b-GGUF scores 60.2/100 for agentic workflows. It runs at about 21.7 tok/s, so if you want more speed, muse-glimmer:latest is faster (~34.5 tok/s) and still scores well for agentic workflows (93.0/100).
- How fast is unsloth/gpt-oss-20b-GGUF for local inference?
- Across 3 community benchmark runs, unsloth/gpt-oss-20b-GGUF reaches up to 23.0 tok/s and averages 21.7 tok/s, with the fastest results on Intel(R) Arc(TM) 140V GPU (16GB).
- How much memory does unsloth/gpt-oss-20b-GGUF need?
- The leanest observed configuration used about 9.8 GB of memory.
- Which tools have been used to run unsloth/gpt-oss-20b-GGUF?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.