Qwen 3.6 35B-A3B

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/Qwen3.6-35B-A3B-GGUF:IQ1_Mollama · IQ1_M · 9.4 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:IQ2_XXSollama · IQ2_XXS · 10.0 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:IQ3_XXSollama · IQ3_XXS · 12.3 GiB · quantizer (unsloth)

lmstudio-community/Qwen3.6-35B-A3B-MLX-4bitmlx · 4BIT · 19.0 GiB · quantizer (lmstudio-community)

hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_Sollama · Q4_K_S · 19.5 GiB · quantizer (unsloth)

hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q4_K_Mollama · Q4_K_M · 20.6 GiB · quantizer (unsloth)

nvidia/Qwen3.6-35B-A3B-NVFP4vllm · NVFP4 · 21.8 GiB · quantizer (nvidia)

RedHatAI/Qwen3.6-35B-A3B-NVFP4vllm · W4A4 · 23.3 GiB · quantizer (RedHatAI)

QuantTrio/Qwen3.6-35B-A3B-AWQvllm · AWQ · 23.7 GiB · quantizer (QuantTrio)

lmstudio-community/Qwen3.6-35B-A3B-MLX-6bitmlx · 6BIT · 27.1 GiB · quantizer (lmstudio-community)

hf.co/unsloth/Qwen3.6-35B-A3B-GGUF:Q8_0ollama · Q8_0 · 34.4 GiB · quantizer (unsloth)

Qwen/Qwen3.6-35B-A3B-FP8vllm · FP8 · 34.9 GiB · vendor (Qwen)

lmstudio-community/Qwen3.6-35B-A3B-MLX-8bitmlx · 8BIT · 35.1 GiB · quantizer (lmstudio-community)

unsloth/Qwen3.6-35B-A3B-GGUF:BF16llamacpp · BF16 · 64.6 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.

Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressivenot measured Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUFnot measured Qwen3.6-35B-A3B-oQ4e-mtpnot measured Qwen3.6-35B-A3B-NVFP4-Fastnot measured Qwen3.6-35B-A3B-MTP-GGUFnot measured