LLM EXPLORER 59,766 MODELS INDEXED

GLM 5.3 Flash MLX OQ4 MTP by Vontra

By Vontra · 0 downloads
HF Repo ↗ Copy URL

GLM 5.3 Flash MLX OQ4 MTP is an open-source language model by Vontra. Features: 51.8b LLM, VRAM: 184.7GB, License: mit, LLM Explorer Score: 0.26.

  Arxiv:2602.15763   4-bit   Apple-silicon Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla...   Conversational   En   Glm   Glm5   Glm5-next   Glm5 next   Image-text-to-text   Mixed-precision   Mixture-of-experts   Mlx   Mlx-vlm   Multimodal   Native-mtp   Omlx   Oq   Quantized   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Vision   Vision-language   Zh
Model Card on HF 🤗: https://huggingface.co/Vontra/GLM-5.3-Flash-MLX-oQ4-MTP 

GLM 5.3 Flash MLX OQ4 MTP Parameters and Internals

LLM NameGLM 5.3 Flash MLX OQ4 MTP
Repository 🤗https://huggingface.co/Vontra/GLM-5.3-Flash-MLX-oQ4-MTP 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size51.8b
Required VRAM184.7 GB
Updated2026-08-28
MaintainerVontra
Model Typeglm5_next
Model Files  5.0 GB: 1-of-35   5.0 GB: 2-of-35   5.7 GB: 3-of-35   5.4 GB: 4-of-35   5.4 GB: 5-of-35   5.4 GB: 6-of-35   5.4 GB: 7-of-35   5.4 GB: 8-of-35   5.4 GB: 9-of-35   5.4 GB: 10-of-35   5.4 GB: 11-of-35   5.4 GB: 12-of-35   5.4 GB: 13-of-35   5.4 GB: 14-of-35   5.4 GB: 15-of-35   5.4 GB: 16-of-35   5.4 GB: 17-of-35   5.4 GB: 18-of-35   5.4 GB: 19-of-35   5.4 GB: 20-of-35   5.4 GB: 21-of-35   5.4 GB: 22-of-35   5.4 GB: 23-of-35   5.4 GB: 24-of-35   5.4 GB: 25-of-35   5.4 GB: 26-of-35   5.4 GB: 27-of-35   5.4 GB: 28-of-35   5.4 GB: 29-of-35   5.4 GB: 30-of-35   5.4 GB: 31-of-35   5.4 GB: 32-of-35   5.4 GB: 33-of-35   5.4 GB: 34-of-35   1.6 GB: 35-of-35
Supported Languagesen zh
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>