Qwen 3.5 4B

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/Qwen3.5-4B-GGUF:IQ2_XXSollama · IQ2_XXS · 1.4 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-4B-GGUF:IQ2_Mollama · IQ2_M · 1.6 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-4B-GGUF:IQ3_XXSollama · IQ3_XXS · 1.8 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_0ollama · Q4_0 · 2.4 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-4B-GGUF:Q4_K_Mollama · Q4_K_M · 2.6 GiB · quantizer (unsloth)

mlx-community/Qwen3.5-4B-MLX-4bitmlx · 4BIT · 2.8 GiB · quantizer (mlx-community)

hf.co/unsloth/Qwen3.5-4B-GGUF:Q8_0ollama · Q8_0 · 4.2 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.5-4B-GGUF:BF16ollama · BF16 · 7.8 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.

Qwen3.5-4B-OptiQ-4bitnot measured