LLMs · Alibaba

Qwen3.5 35B-A3B

Name: Qwen3.5 35B-A3B
Author: Alibaba

Parameters: 36B (3.0B active)
Architecture: Mixture of experts
Max context: 256K tokens
License: apache-2.0
Released: 2026-02

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

ollama run qwen3.5:35b

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Qwen3.5-35B-A3B-GGUF

Original weights · Hugging Face

Full-precision files from Alibaba, for fine-tuning, vLLM, Transformers.

huggingface.co/Qwen/Qwen3.5-35B-A3B (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Alibaba. The weights themselves download from Hugging Face.

github.com/QwenLM/Qwen3.8 (opens in a new tab)

git clone https://github.com/QwenLM/Qwen3.8

Qwen’s current repo: Qwen3.5 and Qwen3.6 redirect here.

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: hybrid: only the full-attention layers (1 in 4) keep a KV cache; the rest use linear attention.

Quantization	Quality	Weights	Total at 8K context	Total at 32K context	Download
`Q2_K`	Low	14.4 GB	15.1 GB	15.7 GB	GGUF (UD-Q2_K_XL) (opens in a new tab)
`Q3_K_M`	Low	17.6 GB	18.4 GB	18.9 GB	GGUF (opens in a new tab)
`Q4_K_M`	Good	21.9 GB	22.7 GB	23.2 GB	GGUF (opens in a new tab)
`Q5_K_M`	High	25.5 GB	26.3 GB	26.8 GB	GGUF (opens in a new tab)
`Q6_K`	High	29.5 GB	30.2 GB	30.8 GB	GGUF (opens in a new tab)
`Q8_0`	Very high	38.1 GB	38.9 GB	39.4 GB	GGUF (opens in a new tab)
`F16`	Full	71.9 GB	72.7 GB	73.2 GB	GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Qwen3.5 35B-A3B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at Q2_K.

Grade · points	Hardware	Quant	Memory	Speed	Fit
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA RTX PRO 6000 Blackwell	`F16`	77.5 GB / 96.0 GB	86.0 tok/s	Runs well
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Apple M1 Max (64 GB)	`Q6_K`	34.1 GB / 48.0 GB	48.9 tok/s	Runs well
96 ptsExcellent (S) · 96 of 100 points: Model quality 41.4/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15	Apple M4 Max (64 GB)	`Q6_K`	34.1 GB / 48.0 GB	66.7 tok/s	Runs well
95 ptsExcellent (S) · 95 of 100 points: Model quality 40.6/45, Memory fit 25.0/25, Speed 14.9/15, Memory use 15.0/15	Apple M4 Pro (48 GB)	`Q5_K_M`	29.2 GB / 36.0 GB	39.7 tok/s	Runs well
95 ptsExcellent (S) · 95 of 100 points: Model quality 41.4/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 5090	`Q6_K`	31.8 GB / 32.0 GB	254 tok/s	Tight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	AMD Radeon RX 7900 XTX	`Q4_K_M`	23.9 GB / 24.0 GB	169 tok/s	Tight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 3090	`Q4_K_M`	23.9 GB / 24.0 GB	191 tok/s	Tight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 39.8/45, Memory fit 24.0/25, Speed 15.0/15, Memory use 15.0/15	NVIDIA GeForce RTX 4090	`Q4_K_M`	23.9 GB / 24.0 GB	206 tok/s	Tight fit
93 ptsExcellent (S) · 93 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 11.2/15	Apple M4 Max (128 GB)	`Q8_0`	46.6 GB / 96.0 GB	49.0 tok/s	Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 41.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 8.1/15	Apple M2 Ultra (192 GB)	`Q8_0`	50.4 GB / 144 GB	71.7 tok/s	Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.