unsloth
/

Qwen3.5-122B-A10B-GGUF

Image-Text-to-Text

Model card Files Files and versions

Resources

View closed (4)

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

#13 opened about 1 month ago by

Perplexity Q5_K_S vs NVFP4 on Qwen 3.5 122B

#18 opened 15 days ago by

I'm trying to run Qwen3.5 122b. The Unsloth quantized models are not starting up.

#16 opened about 1 month ago by

Is Q3_XXX actually IQ3_XXX?

#15 opened about 1 month ago by

'No user query found in messages.'

#14 opened about 1 month ago by

March 5 updates compared to Feb ones?

#11 opened about 1 month ago by

Anyone tried the Vlm in IKlamacpp fork?

#10 opened about 1 month ago by

KLD/PPL of quants

#8 opened about 1 month ago by

krampenschiesser

SOLVED - Abysmal performance on 1x24GB 3090 Ti + 48GB RAM

#6 opened about 1 month ago by

Use --reasoning-budget 0 for instruct mode

#5 opened about 1 month ago by

Performance report for UD-Q4_K_XL with 72GB VRAM: 65 t/s

#3 opened about 1 month ago by

very fast!!!

#2 opened about 1 month ago by

Mixed MXFP4 and Q4

#1 opened about 1 month ago by

krampenschiesser