Model benchmarks
text-model local LLM performance
As of October 2026, text-model runs at up to 95.4 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
95.4 tok/s
Average speed
86.4 tok/s
Avg PP
646.5 tok/s
Min memory
15.4 GB
Max context
65,536 tokens
Avg output / run
17,849 tokens
Avg runtime / run
3m 36s
Avg quality
74.2
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 | 69.6 | 74.2 | 80.1 |
| Agent Workflow | 60.2 | 68.4 | 79.7 |
| Code Generation | 63.6 | 67.3 | 72.9 |
| Role Play & Narrative | 82.5 | 84.6 | 86.3 |
| Research & Analysis | 71.0 | 76.3 | 81.6 |
Performance by hardware and tool
Every hardware/tool/quantization combination text-model has been benchmarked on, ranked by peak token generation speed. Last updated October 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA RTX A2000 12GB | OpenAI-compatible | — | 95.4 tok/s | 86.4 tok/s | 15.4 GB | 65,536 tokens | 74.2 | 3 |
Benchmark runs
All 3 text-model runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is text-model good for coding?
- In our benchmarks, text-model scores 67.3/100 for coding. It runs at about 86.4 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e is faster (~107.9 tok/s) and still scores well for coding (81.5/100).
- Is text-model good for agentic (tool-using) tasks?
- In our benchmarks, text-model scores 68.4/100 for agentic workflows. It runs at about 86.4 tok/s, so if you want more speed, qwen3.8-flash-next-iq3_s is faster (~116.8 tok/s) and still scores well for agentic workflows (88.4/100).
- How fast is text-model for local inference?
- Across 3 community benchmark runs, text-model reaches up to 95.4 tok/s and averages 86.4 tok/s, with the fastest results on NVIDIA RTX A2000 12GB.
- How much memory does text-model need?
- The leanest observed configuration used about 15.4 GB of memory.
- Which tools have been used to run text-model?
- Benchmarks were submitted using OpenAI-compatible. Results are community-contributed and updated as new runs arrive.