unsloth
/

Qwen3-235B-A22B-GGUF

Text Generation

Model card Files Files and versions

Resources

View closed (0)

Amazing, uses humble 255Gb RAM on my ancient 2014 Xeon PC for Q8

#15 opened about 2 hours ago by

Quality benefits of UD-Q4_K_XL vs Q5_K_M vs Q6_K for this model?

#14 opened about 7 hours ago by

Why changes in the past 0-24h here vs. not on Qwen3-235B-A22B-128K-GGUF?

#13 opened about 7 hours ago by

Finetuning possible?

#12 opened about 15 hours ago by

Why are XL quants smaller than M quants?

#11 opened about 22 hours ago by

config.json "max_position_embeddings": 40960,

#10 opened 2 days ago by

how to disable <think> with llama.cpp

#9 opened 3 days ago by

It seems like model have serious repetition issues (both gguf and on openrouter)

#8 opened 3 days ago by

[Qwen3-235B-A22B-UD-Q4_K_XL.gguf] UD Quant seems to be invalid.

#7 opened 3 days ago by

Test on 3090 + Tesla P40 (48gb vram total) + 64gb ram (Q2K)

#6 opened 3 days ago by

Ud quants please🥺

#5 opened 3 days ago by

ValueError: Cannot use chat template functions because tokenizer.chat_template is not set and no template argument was passed!

#4 opened 3 days ago by

Do the Q4 quants work? On the 30b moe it says not to use them.

#3 opened 3 days ago by

UD quants missing some files

#2 opened 3 days ago by

MLDataScientist

Add languages tag

#1 opened 3 days ago by

de-francophones