unsloth/Qwen3.5-35B-A3B-GGUF

Mar 5 - 'Final' Update: iMatrix + Benchmarks + New quant algo

#31 opened about 1 month ago by

danielhanchen

Feb 27: GGUF Update + Tool-calling fixes + Benchmarks

pinned

🚀🔥 12

24

#10 opened about 2 months ago by

danielhanchen

Getting ///////// output with this model across all quants

#45 opened 5 days ago by

dmcleod97

Why this model refuses to provide surgery procedure?

#44 opened 7 days ago by

JLouisBiz

Has anyone finally gotten this model to work properly or are we still waiting for another update?

#42 opened 24 days ago by

systems-u

Telemetry tips for Claude code with Qwen

❤️🔥 2

#41 opened 24 days ago by

tstello

New to all things HF and AI, but bugs I am familiar with. ROCm: illegal memory access. Model: Qwen3.5-35B-A3B-Q4_K_M

1

#40 opened 29 days ago by

jwallgood

Is there a way to enable/disable thinking at the request level?

1

#39 opened about 1 month ago by

septerium

why qwen3.5 think so long？

#38 opened about 1 month ago by

sysy007uuu2

What happened to Qwen3.5-35B-A3B-UD-Q4_K_M.gguf ?

👍 1

#37 opened about 1 month ago by

martinsky

Fix Jinja Template: Add support for multiple System messages and Add Support for Developer messages

1

#36 opened about 1 month ago by

muoikai

Usage for image description

2

#35 opened about 1 month ago by

hamster007

Fix Jinja Template: Add support for multiple System messages and Add Support for Developer messages

👍 2

#34 opened about 1 month ago by

q177

Is docs page down?

1

#33 opened about 1 month ago by

Glee951

Quick question for the team about Q8_K_XL

👀 4

4

#30 opened about 1 month ago by

jswiftie

Multimodal not detecting in LM Studio

#29 opened about 1 month ago by

teddyspaghetti

Verbose looping

2

#28 opened about 1 month ago by

islameissa

Bug: Model does not produce <think></think> tokens when enable_thinking=true

1

#26 opened about 1 month ago by

mohamedemam

March 3, 2026 updates ?

7

#25 opened about 1 month ago by

BitBuilder

Why did the Qwen3.5 model I used experience an automatic exit during loading?

1

#24 opened about 1 month ago by

yangfan19910901

Still some tool calling issues

➕ 2

7

#22 opened about 1 month ago by

LadyJun

Reasoning breaks at middle of no where

#21 opened about 1 month ago by

jackson145258116

Is Image supported in this model?

2

#20 opened about 1 month ago by

sanjilover

Endless looping while analyzing image and thinking.

➕ 1

6

#19 opened about 2 months ago by

0707intel

LM Studio does not support the newly updated chat template

2

#18 opened about 2 months ago by

FORNAX20

How to use Qwen3.5 GGUF in transformers?

1

#17 opened about 2 months ago by

Jackson404

Is Q8_0 gone?

2

#16 opened about 2 months ago by

PhilippeEiffel

Vllm support

8

#15 opened about 2 months ago by

deece

Qwen3.5-35B-A3B-GGUF:UD-Q4_K_M does not work in Ollama 0.17.4

2

#14 opened about 2 months ago by

Arete7

Suggestion: Preserve ssm_alpha and ssm_beta in BF16 for Q8_0 Quants (Fix for Long-Context Degradation)

👍 1

3

#13 opened about 2 months ago by

wize-1

hello

#12 opened about 2 months ago by

Vyn25

Add support for developer role in chat template (Codex compatibility)

🔥 4

1

#9 opened about 2 months ago by

xangma

hi llama.cpp had a new optimize for qwen3.5moe. commit id:b68d751

👍 7

1

#8 opened about 2 months ago by

Simon716

Is there some helpful regex to offload all MoE layers to the CPU?

4

#7 opened about 2 months ago by

hdnh2006

TQ1 quant?

👍 2

3

#6 opened about 2 months ago by

sergeysi

Update: Should now be Fixed - Bug in UD-Q4_K_XL recipe using MXFP4 for attn tensors and experts?

👍 8

26

#5 opened about 2 months ago by

ubergarm

Prompt cache not working correctly

👀👍 6

1

#4 opened about 2 months ago by

guiopen

Coding parameters used for Goose and Zed

2

#3 opened about 2 months ago by

dugrema

llama cpp Error: Unknown (built-in) filter 'items' for type String

9

#2 opened about 2 months ago by

fullstack

Benchmarks

👍 6

1

#1 opened about 2 months ago by

coder543