LLM EXPLORER 59,962 MODELS INDEXED

GLM 5.3 Flash MLX 4bit by pipenetwork

By pipenetwork · 2535 downloads
HF Repo ↗ Copy URL

GLM 5.3 Flash MLX 4bit is an open-source language model by pipenetwork. Features: 49.6b LLM, VRAM: 0.8GB, License: mit, Quantized, LLM Explorer Score: 0.47, ELO: 1286.

  4-bit   4bit   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-4bit 

GLM 5.3 Flash MLX 4bit 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 4bit Parameters and Internals

LLM NameGLM 5.3 Flash MLX 4bit
Repository 🤗https://huggingface.co/pipenetwork/GLM-5.3-Flash-MLX-4bit 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size49.6b
Required VRAM0.8 GB
Updated2026-08-30
Maintainerpipenetwork
Model Typeglm5_next
Model Files  11.0 GB   11.1 GB   11.2 GB   11.2 GB   11.1 GB   11.2 GB   11.2 GB   11.1 GB   11.2 GB   11.2 GB   11.1 GB   11.2 GB   11.2 GB   11.1 GB   11.2 GB   10.0 GB   0.8 GB
Quantization Type4bit
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>