LLM EXPLORER 59,962 MODELS INDEXED

GLM 5.3 Flash MLX Mixed 4 8bit by pipenetwork

By pipenetwork · 1954 downloads
HF Repo ↗ Copy URL

GLM 5.3 Flash MLX Mixed 4 8bit is an open-source language model by pipenetwork. Features: 50.7b LLM, VRAM: 1.1GB, License: mit, Quantized, LLM Explorer Score: 0.47, ELO: 1286.

  4-bit   8bit   Apple-silicon Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla...   Conversational   Glm5 next   Image-text-to-text   Mixture-of-experts   Mlx   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-mixed-4_8bit 

GLM 5.3 Flash MLX Mixed 4 8bit Benchmarks

LMSys ELO 1286 vs 1272 (so35) 1.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

GLM 5.3 Flash MLX Mixed 4 8bit Parameters and Internals

LLM NameGLM 5.3 Flash MLX Mixed 4 8bit
Repository 🤗https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-mixed-4_8bit 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size50.7b
Required VRAM1.1 GB
Updated2026-08-30
Maintainerpipenetwork
Model Typeglm5_next
Model Files  10.8 GB   10.0 GB   11.2 GB   10.0 GB   11.2 GB   10.0 GB   11.2 GB   10.1 GB   11.2 GB   10.0 GB   11.2 GB   10.0 GB   11.2 GB   10.0 GB   11.2 GB   10.1 GB   11.2 GB   1.1 GB
Quantization Type8bit
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>