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

6,415 tokens

Best quality

86.9

Benchmark runs

3

GPUs tested

1

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.

HardwareToolQuantBest tok/sAvg tok/sMemoryContextQualityRuns
Apple M5 MaxOllamaQ4_K_M19.6 tok/s16.4 tok/s26.1 GB6,415 tokens78.93

Frequently asked questions

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.