GLM-5.3 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-5.3-GGUF:IQ1_Sllamacpp · IQ1_S · 201.8 GiB · quantizer (unsloth)

unsloth/GLM-5.3-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 262.3 GiB · quantizer (unsloth)

unsloth/GLM-5.3-GGUF:IQ4_XSllamacpp · IQ4_XS · 340.2 GiB · quantizer (unsloth)

Inferact/GLM-5.3-NVFP4vllm · NVFP4 · 432.9 GiB · quantizer (Inferact)

unsloth/GLM-5.3-GGUF:Q4_K_XLllamacpp · Q4_K_XL · 435.2 GiB · quantizer (unsloth)

zai-org/GLM-5.3vllm · FP8 · 703.7 GiB · vendor (zai-org)

unsloth/GLM-5.3-GGUF:Q8_0llamacpp · Q8_0 · 746.3 GiB · quantizer (unsloth)

zai-org/GLM-5.3-BF16vllm · BF16 · 1403.2 GiB · vendor (zai-org)

unsloth/GLM-5.3-GGUF:BF16llamacpp · BF16 · 1404.4 GiB · quantizer (unsloth)

orcarouter/GLM-5.3-MLXmlx · 4BIT · 2122.4 GiB · quantizer (orcarouter)

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-5.3-FP8not measured