LLM EXPLORER 65,695 MODELS INDEXED

P1 VL 30B A3B 8bit by mlx-community

By mlx-community · 36 downloads
HF Repo ↗ Copy URL

P1 VL 30B A3B 8bit is an open-source language model by mlx-community. Features: 30b LLM, VRAM: 33.5GB, License: apache-2.0, Quantized.

  8-bit   8bit Base model:prime-rl/p1-vl-30b-... Base model:quantized:prime-rl/...   Conversational   Image-text-to-text   Mlx   Olympiad   Physics   Quantized   Qwen3 vl moe   Reasoning   Region:us   Safetensors   Science   Sharded   Tensorflow   Vision   Vision-language
Model Card on HF 🤗: https://huggingface.co/mlx-community/P1-VL-30B-A3B-8bit 

P1 VL 30B A3B 8bit Parameters and Internals

LLM NameP1 VL 30B A3B 8bit
Repository 🤗https://huggingface.co/mlx-community/P1-VL-30B-A3B-8bit 
Base Model(s)  P1 VL 30B A3B   PRIME-RL/P1-VL-30B-A3B
Model Size30b
Required VRAM33.5 GB
Updated2026-10-27
Maintainermlx-community
Model Typeqwen3_vl_moe
Model Files  5.4 GB: 1-of-7   5.3 GB: 2-of-7   5.3 GB: 3-of-7   5.3 GB: 4-of-7   5.3 GB: 5-of-7   5.3 GB: 6-of-7   1.6 GB: 7-of-7
Quantization Type8bit
Model ArchitectureQwen3VLMoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to P1 VL 30B A3B 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 VL 30B A3B Instruct 4bit0K / 18.3 GB9258
Bu 30B A3b Preview 4bit0K / 18.3 GB524
Qwen3 VL 30B A3B Instruct 8bit0K / 33.5 GB2313
Qwen3 VL 30B A3B Thinking 4bit0K / 18.3 GB701
Qwen3 VL 30B A3B Instruct 6bit0K / 25.8 GB722
Qwen3 VL 30B A3B Thinking 3bit0K / 14.5 GB401
Qwen3 VL 30B A3B Instruct0K / 62.3 GB488106591
Qwen3 VL 30B A3B Instruct AWQ0K / 17.9 GB118470445
Qwen3 VL 30B A3B Instruct FP80K / 32.2 GB734631115
Qwen3 VL 30B A3B Thinking0K / 62.3 GB67001200
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/P1-VL-30B-A3B-8bit.