Model benchmarks

qwen/qwen3.6-35b-a3b local LLM performance

As of July 2026, qwen/qwen3.6-35b-a3b runs at up to 46.1 tok/s for local inference (best of 8 community benchmark runs across 1 GPU).

LM Studio

Model size

35B

Peak speed

46.1 tok/s

Average speed

29.6 tok/s

Min memory

17.1 GB

Max context

65,536 tokens

Best quality

92.6

Benchmark runs

8

GPUs tested

1

Performance by hardware and tool

Every hardware/tool/quantization combination qwen/qwen3.6-35b-a3b has been benchmarked on, ranked by peak token generation speed. Last updated July 2026.

HardwareToolQuantBest tok/sAvg tok/sMemoryContextQualityRuns
AMD Radeon RX 7900 XTXLM Studio46.1 tok/s31.1 tok/s17.1 GB65,536 tokens69.86
CPU onlyLM Studio25.0 tok/s24.9 tok/s17.1 GB7,039 tokens79.32

Frequently asked questions

How fast is qwen/qwen3.6-35b-a3b for local inference?
Across 8 community benchmark runs, qwen/qwen3.6-35b-a3b reaches up to 46.1 tok/s and averages 29.6 tok/s, with the fastest results on AMD Radeon RX 7900 XTX.
How much memory does qwen/qwen3.6-35b-a3b need?
The leanest observed configuration used about 17.1 GB of memory.
Which tools have been used to run qwen/qwen3.6-35b-a3b?
Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.