Model benchmarks
qwen3.6:35b local LLM performance
As of May 2026, qwen3.6:35b runs at up to 19.6 tok/s for local inference (best of 3 community benchmark runs across 1 GPU).
OllamaQ4_K_M
Model size
36.0B
Peak speed
19.6 tok/s
Average speed
16.4 tok/s
Min memory
26.1 GB
Max context
65,536 tokens
Avg quality
77.5
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 | 77.1 | 77.5 | 77.8 |
| Agent Workflow | 66.5 | 73.7 | 81.5 |
| Code Generation | 68.8 | 72.7 | 75.2 |
| Role Play & Narrative | 84.0 | 85.4 | 86.6 |
| Research & Analysis | 75.6 | 78.4 | 80.3 |
Performance by hardware and tool
Every hardware/tool/quantization combination qwen3.6:35b has been benchmarked on, ranked by peak token generation speed. Last updated May 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| Apple M5 Max | Ollama | Q4_K_M | 19.6 tok/s | 16.4 tok/s | 26.1 GB | 65,536 tokens | 77.5 | 3 |
Frequently asked questions
- Is qwen3.6:35b good for coding?
- In our benchmarks, qwen3.6:35b scores 72.7/100 for coding. It runs at about 16.4 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for coding (66.9/100).
- Is qwen3.6:35b good for agentic (tool-using) tasks?
- In our benchmarks, qwen3.6:35b scores 73.7/100 for agentic workflows. It runs at about 16.4 tok/s, so if you want more speed, Gemma4:E2B/QAT-MTP@131K is faster (~303.9 tok/s) and still scores well for agentic workflows (71.7/100).
- How fast is qwen3.6:35b for local inference?
- Across 3 community benchmark runs, qwen3.6:35b reaches up to 19.6 tok/s and averages 16.4 tok/s, with the fastest results on Apple M5 Max.
- How much memory does qwen3.6:35b need?
- The leanest observed configuration used about 26.1 GB of memory (quantizations tested: Q4_K_M).
- Which tools have been used to run qwen3.6:35b?
- Benchmarks were submitted using Ollama. Results are community-contributed and updated as new runs arrive.