Model benchmarks
Qwen-EfficientThink_t1p95k20m0 local LLM performance
As of November 2026, Qwen-EfficientThink_t1p95k20m0 runs at up to 39.1 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
Unknown
Peak speed
39.1 tok/s
Average speed
38.5 tok/s
Avg PP
685.8 tok/s
Min memory
63.0 GB
Max context
32,768 tokens
Avg output / run
28,540 tokens
Avg runtime / run
11m 33s
Avg quality
82.3
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 | 80.8 | 82.3 | 83.7 |
| Agent Workflow | 86.8 | 87.6 | 88.3 |
| Code Generation | 71.3 | 74.1 | 76.9 |
| Role Play & Narrative | 83.2 | 83.6 | 84.1 |
| Research & Analysis | 79.7 | 83.8 | 87.9 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen-EfficientThink_t1p95k20m0 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 |
|---|---|---|---|---|---|---|---|---|
| Tesla V100-PCIE-32GB | llama.cpp | — | 39.1 tok/s | 38.5 tok/s | 63.0 GB | 32,768 tokens | 82.3 | 2 |
Benchmark runs
All 2 Qwen-EfficientThink_t1p95k20m0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen-EfficientThink_t1p95k20m0 good for coding?
- In our benchmarks, Qwen-EfficientThink_t1p95k20m0 scores 74.1/100 for coding. It runs at about 38.5 tok/s, so if you want more speed, local-qwen is faster (~60.2 tok/s) and still scores well for coding (84.8/100).
- Is Qwen-EfficientThink_t1p95k20m0 good for agentic (tool-using) tasks?
- In our benchmarks, Qwen-EfficientThink_t1p95k20m0 scores 87.6/100 for agentic workflows. It runs at about 38.5 tok/s, so if you want more speed, granite-4.2-8b-Q4_K_L is faster (~71.6 tok/s) and still scores well for agentic workflows (92.9/100).
- How fast is Qwen-EfficientThink_t1p95k20m0 for local inference?
- Across 2 community benchmark runs, Qwen-EfficientThink_t1p95k20m0 reaches up to 39.1 tok/s and averages 38.5 tok/s, with the fastest results on Tesla V100-PCIE-32GB.
- How much memory does Qwen-EfficientThink_t1p95k20m0 need?
- The leanest observed configuration used about 63.0 GB of memory.
- Which tools have been used to run Qwen-EfficientThink_t1p95k20m0?
- Benchmarks were submitted using llama.cpp. Results are community-contributed and updated as new runs arrive.