Model benchmarks
Qwen3.5-2B-GGUF-Q8_0 local LLM performance
As of November 2026, Qwen3.5-2B-GGUF-Q8_0 runs at up to 38.3 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
Model size
2B
Peak speed
38.3 tok/s
Average speed
38.2 tok/s
Avg PP
1996.4 tok/s
Min memory
n/a
Max context
16,384 tokens
Avg output / run
7,876 tokens
Avg runtime / run
3m 29s
Avg quality
38.9
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 | 34.9 | 38.9 | 42.9 |
| Agent Workflow | 37.0 | 50.9 | 64.9 |
| Code Generation | 14.6 | 19.6 | 24.6 |
| Role Play & Narrative | 38.4 | 42.0 | 45.7 |
| Research & Analysis | 39.4 | 42.9 | 46.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination Qwen3.5-2B-GGUF-Q8_0 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 2050 | Lemonade | Q8_0 | 38.3 tok/s | 38.2 tok/s | n/a | 16,384 tokens | 38.9 | 2 |
Benchmark runs
All 2 Qwen3.5-2B-GGUF-Q8_0 runs submitted so far — expand one for its hardware, quality breakdown and per-scenario detail.
Frequently asked questions
- Is Qwen3.5-2B-GGUF-Q8_0 good for coding?
- In our benchmarks, Qwen3.5-2B-GGUF-Q8_0 scores 19.6/100 for coding. It runs at about 38.2 tok/s, so if you want more speed, turbo is faster (~124.1 tok/s) and still scores well for coding (85.3/100).
- Is Qwen3.5-2B-GGUF-Q8_0 good for agentic (tool-using) tasks?
- In our benchmarks, Qwen3.5-2B-GGUF-Q8_0 scores 50.9/100 for agentic workflows. It runs at about 38.2 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 Qwen3.5-2B-GGUF-Q8_0 for local inference?
- Across 2 community benchmark runs, Qwen3.5-2B-GGUF-Q8_0 reaches up to 38.3 tok/s and averages 38.2 tok/s, with the fastest results on NVIDIA GeForce RTX 2050.
- Which tools have been used to run Qwen3.5-2B-GGUF-Q8_0?
- Benchmarks were submitted using Lemonade. Results are community-contributed and updated as new runs arrive.