GLM-4.6 BASE

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.

unsloth/GLM-4.6-GGUF:IQ1_Sllamacpp · IQ1_S · 90.3 GiB · quantizer (unsloth)

unsloth/GLM-4.6-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 107.5 GiB · quantizer (unsloth)

unsloth/GLM-4.6-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 134.8 GiB · quantizer (unsloth)

mlx-community/GLM-4.6-4bitmlx · 4BIT · 184.9 GiB · quantizer (mlx-community)

lukealonso/GLM-4.6-NVFP4vllm · NVFP4 · 187.0 GiB · quantizer (lukealonso)

unsloth/GLM-4.6-GGUF:Q4_0llamacpp · Q4_0 · 188.3 GiB · quantizer (unsloth)

unsloth/GLM-4.6-GGUF:Q4_K_Mllamacpp · Q4_K_M · 200.8 GiB · quantizer (unsloth)

mlx-community/GLM-4.6-5bitmlx · 5BIT · 226.0 GiB · quantizer (mlx-community)

zai-org/GLM-4.6-FP8vllm · FP8 · 336.5 GiB · vendor (zai-org)

unsloth/GLM-4.6-GGUF:Q8_0llamacpp · Q8_0 · 353.3 GiB · quantizer (unsloth)

zai-org/GLM-4.6vllm · BF16 · 664.6 GiB · vendor (zai-org)

unsloth/GLM-4.6-GGUF:BF16llamacpp · BF16 · 664.7 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.

GLM-4.6-Derestricted-v3not measured