GLM-4.7 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.

hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ1_Sollama · IQ1_S · 8.6 GiB · quantizer (unsloth)

hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ2_XXSollama · IQ2_XXS · 9.8 GiB · quantizer (unsloth)

hf.co/unsloth/GLM-4.7-Flash-GGUF:IQ3_XXSollama · IQ3_XXS · 12.0 GiB · quantizer (unsloth)

mlx-community/GLM-4.7-Flash-4bitmlx · 4BIT · 15.7 GiB · quantizer (mlx-community)

hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_0ollama · Q4_0 · 16.0 GiB · quantizer (unsloth)

hf.co/unsloth/GLM-4.7-Flash-GGUF:Q4_K_Mollama · Q4_K_M · 17.1 GiB · quantizer (unsloth)

QuantTrio/GLM-4.7-Flash-AWQvllm · AWQ · 18.4 GiB · quantizer (QuantTrio)

GadflyII/GLM-4.7-Flash-NVFP4vllm · W4A4 · 19.0 GiB · quantizer (GadflyII)

lmstudio-community/GLM-4.7-Flash-MLX-6bitmlx · 6BIT · 22.7 GiB · quantizer (lmstudio-community)

lmstudio-community/GLM-4.7-Flash-MLX-8bitmlx · 8BIT · 29.6 GiB · quantizer (lmstudio-community)

hf.co/unsloth/GLM-4.7-Flash-GGUF:Q8_0ollama · Q8_0 · 29.7 GiB · quantizer (unsloth)

unsloth/GLM-4.7-Flash-FP8-Dynamicvllm · FP8 · 30.3 GiB · quantizer (unsloth)

unsloth/GLM-4.7-Flash-GGUF:BF16llamacpp · BF16 · 55.8 GiB · quantizer (unsloth)

zai-org/GLM-4.7-Flashvllm · BF16 · 58.2 GiB · vendor (zai-org)

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.

Huihui-GLM-4.7-Flash-abliterated-mlx-4bitnot measured glm-4.7-flashnot measured GLM-4.7-Flashnot measured GLM-4.7-Flash-Codernot measured