GLM-5.3 FLASH

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-Flash-GGUF:IQ1_Sllamacpp · IQ1_S · 86.7 GiB · quantizer (unsloth)

unsloth/GLM-5.3-Flash-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 94.8 GiB · quantizer (unsloth)

hf.co/vcruz305/GLM-5.3-Flash-GGUF:Q2_Kollama · Q2_K · 108.7 GiB · quantizer (vcruz305)

unsloth/GLM-5.3-Flash-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 112.1 GiB · quantizer (unsloth)

hf.co/vcruz305/GLM-5.3-Flash-GGUF:Q4_K_Mollama · Q4_K_M · 179.6 GiB · quantizer (vcruz305)

RedHatAI/GLM-5.3-Flash-NVFP4vllm · W4A4 · 184.3 GiB · quantizer (RedHatAI)

unsloth/GLM-5.3-Flash-GGUF:Q4_K_XLllamacpp · Q4_K_XL · 186.0 GiB · quantizer (unsloth)

nvidia/GLM-5.3-Flash-NVFP4vllm · NVFP4 · 190.4 GiB · quantizer (nvidia)

zai-org/GLM-5.3-Flashvllm · FP8 · 305.8 GiB · vendor (zai-org)

unsloth/GLM-5.3-Flash-GGUF:Q8_0llamacpp · Q8_0 · 317.6 GiB · quantizer (unsloth)

unsloth/GLM-5.3-Flash-GGUF:BF16llamacpp · BF16 · 597.6 GiB · quantizer (unsloth)

orcarouter/GLM-5.3-Flash-MLXmlx · 4BIT · 1057.3 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-flash-ggufnot measured GLM-5.3-Flash-Uncensored-RCO-GSQ-GGUFnot measured Huihui-GLM-5.3-Flash-abliterated-GGUFnot measured GLM-5.3-Flash-oQ4e-mtpnot measured GLM-5.3-Flash-Maya-GGUFnot measured GLM-5.3-Flash-GSQ-RCO-GGUFnot measured GLM-5.3-Flash-MLX-mixed-4_8bitnot measured GLM-5.3-Flash-MLX-4bit-MTPnot measured GLM-5.3-Flash-MLX-oQ4-MTPnot measured