Compare models

Models, side by side.

Size, architecture, licence and context limits for up to four models. Missing details are marked unknown, and evaluation results are not overall ratings.

Choose at least two published models to compare.

Choose two to four

Select models to compare

Choose two to four models to compare.

Qwen

Qwen3.5-35B-A3B-FP8

Qwen/Qwen3.5-35B-A3B-FP8

Select for comparison

Qwen

Qwen3.5-4B

Qwen/Qwen3.5-4B

Select for comparison

Qwen

Qwen3.5-9B

Qwen/Qwen3.5-9B

Select for comparison

DavidAU

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF

Select for comparison

Qwen

Qwen3.6-27B

Qwen/Qwen3.6-27B

Select for comparison

Qwen

Qwen3.6-27B-FP8

Qwen/Qwen3.6-27B-FP8

Select for comparison

Qwen

Qwen3.6-35B-A3B

Qwen/Qwen3.6-35B-A3B

Select for comparison

Qwen

Qwen3.6-35B-A3B-FP8

Qwen/Qwen3.6-35B-A3B-FP8

Select for comparison

nvidia

Qwen3.6-35B-A3B-NVFP4

nvidia/Qwen3.6-35B-A3B-NVFP4

Select for comparison

Qwen

Qwen3.8-27B

Qwen/Qwen3.8-27B

Select for comparison

Qwen

Qwen3.8-27B-FP8

Qwen/Qwen3.8-27B-FP8

Select for comparison

lmstudio-community

Qwen3.8-27B-GGUF

lmstudio-community/Qwen3.8-27B-GGUF

Select for comparison

ggml-org

Qwen3.8-27B-GGUF

ggml-org/Qwen3.8-27B-GGUF

Select for comparison

unsloth

Qwen3.8-27B-GGUF

unsloth/Qwen3.8-27B-GGUF

Select for comparison

ISTA-DASLab

Qwen3.8-27B-GSQ-RCO-GGUF

ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF

Select for comparison

0bserverx

Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

0bserverx/Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF

Select for comparison

cdiamond

Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

cdiamond/Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF

Select for comparison

lmstudio-community

Qwen3.8-27B-MLX-4bit

lmstudio-community/Qwen3.8-27B-MLX-4bit

Select for comparison

lmstudio-community

Qwen3.8-27B-MLX-5bit

lmstudio-community/Qwen3.8-27B-MLX-5bit

Select for comparison

lmstudio-community

Qwen3.8-27B-MLX-6bit

lmstudio-community/Qwen3.8-27B-MLX-6bit

Select for comparison