Model benchmarks
qwen/qwen3-1.7b local LLM performance
As of October 2026, qwen/qwen3-1.7b runs at up to 20.0 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
1.7B
Peak speed
20.0 tok/s
Average speed
19.8 tok/s
Avg PP
543.0 tok/s
Min memory
2.3 GB
Max context
16,384 tokens
Avg output / run
12,512 tokens
Avg runtime / run
17m 47s
Avg quality
38.4
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 | 35.5 | 38.4 | 41.2 |
| Agent Workflow | 46.2 | 47.5 | 48.9 |
| Code Generation | 2.9 | 15.1 | 27.3 |
| Role Play & Narrative | 46.6 | 47.3 | 47.9 |
| Research & Analysis | 42.1 | 43.7 | 45.2 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen/qwen3-1.7b 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 GeForce GTX 1050 | LM Studio | Q4_K_M | 20.0 tok/s | 19.8 tok/s | 2.3 GB | 16,384 tokens | 38.4 | 2 |
Benchmark runs
All 2 qwen/qwen3-1.7b runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen/qwen3-1.7b good for coding?
- In our benchmarks, qwen/qwen3-1.7b scores 15.1/100 for coding. It runs at about 19.8 tok/s, so if you want more speed, tensorfold-qwen38-27b is faster (~25.0 tok/s) and still scores well for coding (84.3/100).
- Is qwen/qwen3-1.7b good for agentic (tool-using) tasks?
- In our benchmarks, qwen/qwen3-1.7b scores 47.5/100 for agentic workflows. It runs at about 19.8 tok/s, so if you want more speed, muse-glimmer:latest is faster (~33.3 tok/s) and still scores well for agentic workflows (91.6/100).
- How fast is qwen/qwen3-1.7b for local inference?
- Across 2 community benchmark runs, qwen/qwen3-1.7b reaches up to 20.0 tok/s and averages 19.8 tok/s, with the fastest results on NVIDIA GeForce GTX 1050.
- How much memory does qwen/qwen3-1.7b need?
- The leanest observed configuration used about 2.3 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run qwen/qwen3-1.7b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.