pipenetwork/GLM-5.3-Flash-MLX-8bit
Image-Text-to-Text • 89B • Updated
GLM-5.3-Flash MLX
Apple Silicon (MLX) builds of GLM-5.3-Flash with a validated, fixed glm5_next runtime: github.com/PipeNetwork/glm53-flash-mlx
Note 334 GB. The anchor (bf16 does not fit a 512 GB Mac): ppl 3.4607 on 289k tokens of wikitext-2.
pipenetwork/GLM-5.3-Flash-MLX-6bit
Image-Text-to-Text • 69B • UpdatedNote 256 GB. Indistinguishable from 8-bit: ppl 3.4646, paired ratio 0.9989 [0.9962, 1.0017], worse on 89/141 windows.
pipenetwork/GLM-5.3-Flash-MLX-mixed-4_8bit
Image-Text-to-Text • 51B • Updated • 2Note 182 GB. ppl 3.5705 (+3.2%): 4-bit experts, 8-bit for the ~9B non-expert weights. Fits a 256 GB Mac.
pipenetwork/GLM-5.3-Flash-MLX-4bit
Image-Text-to-Text • 50B • Updated • 2Note 178 GB. ppl 3.7549 (+8.5%): 4.4 GB smaller than mixed-4_8bit for 5 more points of perplexity.