Model benchmarks
turbo local LLM performance
As of November 2026, turbo runs at up to 135.6 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
135.6 tok/s
Average speed
124.1 tok/s
Avg PP
3419.5 tok/s
Min memory
n/a
Max context
65,536 tokens
Avg output / run
77,357 tokens
Avg runtime / run
10m 7s
Avg quality
89.4
Benchmark runs
2
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 2 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 | 89.4 | 89.4 | 89.4 |
| Agent Workflow | 84.0 | 87.5 | 91.0 |
| Code Generation | 81.6 | 85.3 | 89.0 |
| Role Play & Narrative | 92.0 | 94.1 | 96.2 |
| Research & Analysis | 89.0 | 90.8 | 92.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination turbo has been benchmarked on, ranked by peak token generation speed. Last updated November 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| AMD Radeon AI PRO R9700 | radiance | — | 135.6 tok/s | 124.1 tok/s | n/a | 65,536 tokens | 89.4 | 2 |
Benchmark runs
All 2 turbo runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is turbo good for coding?
- In our benchmarks, turbo scores 85.3/100 for coding. It runs at about 124.1 tok/s, so if you want more speed, ornith-1.5-35b-apex is faster (~149.2 tok/s) and still scores well for coding (83.5/100).
- Is turbo good for agentic (tool-using) tasks?
- In our benchmarks, turbo scores 87.5/100 for agentic workflows. It runs at about 124.1 tok/s, so if you want more speed, swift-1.5-qwen3.8-flash-next-iq3_s is faster (~259.0 tok/s) and still scores well for agentic workflows (88.9/100).
- How fast is turbo for local inference?
- Across 2 community benchmark runs, turbo reaches up to 135.6 tok/s and averages 124.1 tok/s, with the fastest results on AMD Radeon AI PRO R9700.
- Which tools have been used to run turbo?
- Benchmarks were submitted using radiance. Results are community-contributed and updated as new runs arrive.