Qwen 3.5 9B

No machine on this network has measured this model yet. Everything below is what the catalog knows exists — where the weights come from, how large each build is, and whose work it is. Nothing here is a claim about what the model can do; that only appears once a machine has run it and signed the result.

hf.co/unsloth/Qwen3.5-9B-GGUF:IQ2_XXSollama · IQ2_XXS · 3.0 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-9B-GGUF:IQ2_Mollama · IQ2_M · 3.4 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-9B-GGUF:IQ3_XXSollama · IQ3_XXS · 3.7 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_0ollama · Q4_0 · 5.0 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-9B-GGUF:Q4_K_Mollama · Q4_K_M · 5.3 GiB · quantizer (unsloth)

lmstudio-community/Qwen3.5-9B-MLX-4bitmlx · 4BIT · 5.5 GiB · quantizer (lmstudio-community)

AxionML/Qwen3.5-9B-NVFP4vllm · NVFP4 · 8.7 GiB · quantizer (AxionML)

hf.co/unsloth/Qwen3.5-9B-GGUF:Q8_0ollama · Q8_0 · 8.9 GiB · quantizer (unsloth)

lmstudio-community/Qwen3.5-9B-MLX-8bitmlx · 8BIT · 9.7 GiB · quantizer (lmstudio-community)

hf.co/unsloth/Qwen3.5-9B-GGUF:BF16ollama · BF16 · 16.7 GiB · quantizer (unsloth)

derivatives — somebody else's change to these weights

Fine-tunes, merges and abliterations of this member, each its own model with its own page. None of their numbers are counted above.

Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSOREDnot measured Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTPnot measured Huihui-Qwen3.5-9B-abliteratednot measured Qwen3.5-9B-Kimi-k3-Distillednot measured