← GLM-5.2

GLM-5.2 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-5.2-GGUF:IQ1_Sllamacpp · IQ1_S · 201.8 GiB · quantizer (unsloth)
unsloth/GLM-5.2-GGUF:IQ2_XXSllamacpp · IQ2_XXS · 222.1 GiB · quantizer (unsloth)
unsloth/GLM-5.2-GGUF:IQ3_XXSllamacpp · IQ3_XXS · 262.3 GiB · quantizer (unsloth)
mlx-community/GLM-5.2-mxfp4mlx · 4BIT · 368.0 GiB · quantizer (mlx-community)
unsloth/GLM-5.2-GGUF:Q4_K_Sllamacpp · Q4_K_S · 406.5 GiB · quantizer (unsloth)
amd/GLM-5.2-MXFP4vllm · QUARK · 407.9 GiB · quantizer (amd)
inferencerlabs/GLM-5.2-MLX-Q4imlx · BF16 · 416.7 GiB · quantizer (inferencerlabs)
nvidia/GLM-5.2-NVFP4vllm · NVFP4 · 432.9 GiB · quantizer (nvidia)
unsloth/GLM-5.2-GGUF:Q4_K_Mllamacpp · Q4_K_M · 433.8 GiB · quantizer (unsloth)
zai-org/GLM-5.2-FP8vllm · FP8 · 703.7 GiB · vendor (zai-org)
unsloth/GLM-5.2-GGUF:Q8_0llamacpp · Q8_0 · 746.3 GiB · quantizer (unsloth)
zai-org/GLM-5.2vllm · BF16 · 1403.2 GiB · vendor (zai-org)
unsloth/GLM-5.2-GGUF:BF16llamacpp · BF16 · 1404.4 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-5.2-ggufnot measuredGLM-5.2-Alis-MLX-Dynamic-3.5bpwnot measuredGLM-5.2-EXL3-TR3v4-3.5bpw-MTP78not measuredHuihui-GLM-5.2-abliterated-GGUFnot measuredGLM-5.2-0.8B-A0.8Bnot measuredGLM-5.2-E2M1-Furnacenot measuredGLM-5.2-fp8not measuredGLM-5.2-DQ4plus-q8not measuredGLM-5.2-W4AFP8not measuredGLM-5.2-Demolition-q4a4-soul-MLXnot measuredGLM-5.2-MLX-mixed-3_6bitnot measuredGLM-5.2-REAP50-MLX-4bitnot measuredGLM-5.2-ewaste-edition-GGUFnot measuredGLM-5.2-GGUF-2.244bpwnot measuredglm-5.2not measuredGLM-5.2-MaxMin108-GGUFnot measured