Model benchmarks
qwen3-8b-fast local LLM performance
As of November 2026, qwen3-8b-fast runs at up to 114.9 tok/s for local inference (best of 4 community benchmark runs across 1 GPU).
Model size
8B
Peak speed
114.9 tok/s
Average speed
114.4 tok/s
Avg PP
3294.5 tok/s
Min memory
8.5 GB
Max context
65,536 tokens
Avg output / run
5,148 tokens
Avg runtime / run
57s
Avg quality
62.2
Benchmark runs
4
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 4 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 | 57.9 | 62.2 | 66.1 |
| Agent Workflow | 69.5 | 74.7 | 80.1 |
| Code Generation | 27.1 | 41.5 | 54.4 |
| Role Play & Narrative | 69.2 | 75.2 | 84.0 |
| Research & Analysis | 51.6 | 57.5 | 62.7 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3-8b-fast 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 |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 3080 Ti | llama.cpp | — | 114.9 tok/s | 114.5 tok/s | 8.5 GB | 65,536 tokens | 62.0 | 3 |
| NVIDIA GeForce RTX 3080 Ti | OpenAI-compatible | — | 114.0 tok/s | 114.0 tok/s | 8.5 GB | 40,960 tokens | 63.0 | 1 |
Benchmark runs
All 4 qwen3-8b-fast runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is qwen3-8b-fast good for agentic (tool-using) tasks?
- In our benchmarks, qwen3-8b-fast scores 74.7/100 for agentic workflows. It runs at about 114.4 tok/s, so if you want more speed, Tiel-Coder-35B-A3B-MLX-oQ4e-MTP is faster (~151.8 tok/s) and still scores well for agentic workflows (83.0/100).
- How fast is qwen3-8b-fast for local inference?
- Across 4 community benchmark runs, qwen3-8b-fast reaches up to 114.9 tok/s and averages 114.4 tok/s, with the fastest results on NVIDIA GeForce RTX 3080 Ti.
- How much memory does qwen3-8b-fast need?
- The leanest observed configuration used about 8.5 GB of memory.
- Which tools have been used to run qwen3-8b-fast?
- Benchmarks were submitted using OpenAI-compatible, llama.cpp. Results are community-contributed and updated as new runs arrive.