GLM-4.6 V

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/GLM-4.6V-GGUF:IQ1_Sollama · IQ1_S · 34.5 GiB · quantizer (unsloth)

hf.co/unsloth/GLM-4.6V-GGUF:IQ2_XXSollama · IQ2_XXS · 38.4 GiB · quantizer (unsloth)

hf.co/unsloth/GLM-4.6V-GGUF:IQ3_XXSollama · IQ3_XXS · 46.3 GiB · quantizer (unsloth)

unsloth/GLM-4.6V-GGUF:Q3_K_Sllamacpp · Q3_K_S · 47.4 GiB · quantizer (unsloth)

unsloth/GLM-4.6V-GGUF:IQ4_XSllamacpp · IQ4_XS · 54.3 GiB · quantizer (unsloth)

mlx-community/GLM-4.6V-mxfp4mlx · 4BIT · 54.5 GiB · quantizer (mlx-community)

unsloth/GLM-4.6V-GGUF:Q4_0llamacpp · Q4_0 · 56.6 GiB · quantizer (unsloth)

GadflyII/GLM-4.6V-NVFP4vllm · W4A4 · 59.3 GiB · quantizer (GadflyII)

cyankiwi/GLM-4.6V-AWQ-4bitvllm · W4A16 · 60.6 GiB · quantizer (cyankiwi)

hf.co/ggml-org/GLM-4.6V-GGUF:Q4_K_Mollama · Q4_K_M · 65.6 GiB · quantizer (ggml-org)

unsloth/GLM-4.6V-GGUF:Q4_K_Mllamacpp · Q4_K_M · 65.7 GiB · quantizer (unsloth)

mlx-community/GLM-4.6V-6bitmlx · 6BIT · 82.5 GiB · quantizer (mlx-community)

zai-org/GLM-4.6V-FP8vllm · FP8 · 102.4 GiB · vendor (zai-org)

unsloth/GLM-4.6V-GGUF:Q8_0llamacpp · Q8_0 · 105.8 GiB · quantizer (unsloth)

unsloth/GLM-4.6V-GGUF:BF16llamacpp · BF16 · 199.1 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.

GLM-4.6V-4bitnot measured GLM-4.6V-i1-GGUFnot measured glm-4.6vnot measured