~/model/huggingfaceQwen/Qwen3.6-35B-A3B
Alibaba provider

Qwen 3.6 35B A3B

Q2 2026 Qwen3.6 MoE flagship. 35B total, 3B active. Vision + multilingual + tool calling.

Parameters
35B
Family
Alibaba
Context
256K tokens
FP16 weights
70GB
// where you can run it
OllamaLM StudiovLLMMLXoMLX
// hugging face stats (cached daily)
5.9M downloads · 2K likes · license: apache-2.0 · updated 27 days ago

What you need to run this.

$ ./vrambudget --model qwen-3-6-35b-a3b --by quant
FP1670 GB
M3 Max 9696 GB · fitsRTX Pro 600096 GB · fitsM4 Max 128128 GB · fitsM5 Max 128128 GB · fits
Q8_037 GB
RTX A600048 GB · fitsRTX 6000 Ada48 GB · fitsL40S48 GB · fitsRadeon Pro W790048 GB · fits
Q6_K29 GB
RTX A600048 GB · fitsRTX 6000 Ada48 GB · fitsL40S48 GB · fitsRadeon Pro W790048 GB · fits
Q5_K_M24 GB
RTX 509032 GB · fitsRTX A600048 GB · fitsRTX 6000 Ada48 GB · fitsL40S48 GB · fits
Q4_K_M20 GB
RTX 509032 GB · fitsRTX A600048 GB · fitsRTX 6000 Ada48 GB · fitsL40S48 GB · fits

// budgets shown at ctx 8K, concurrency 1, 15% safety headroom. Tune in the calculator →

Alternatives at this size.

$ grep --params similar catalog.json
$ similarYi 34B34B01.AI$ similarQwen 2.5 32B32.5BAlibaba$ similarQwen 2.5 Coder 32B32.5BAlibaba$ similarQwen3 30B A3B30.5BAlibaba

Discussion.

$ gh discussion list

// sign in with github to leave a comment. threads live in the repo's discussions tab.