LLM EXPLORER 57,252 MODELS INDEXED

Agents A1 OptiQ 4bit by mlx-community

By mlx-community · 891 downloads
HF Repo ↗ Copy URL

Agents A1 OptiQ 4bit is an open-source language model by mlx-community. Features: 34.7b LLM, VRAM: 22.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  4-bit   4bit   8bit   Agentic   Apple-silicon Base model:internscience/agent... Base model:quantized:internsci...   Conversational   Image-text-to-text   Mixed-precision   Mlx   Moe   Optiq   Quantized   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Vision   Vision-language   Vlm
Model Card on HF 🤗: https://huggingface.co/mlx-community/Agents-A1-OptiQ-4bit 

Agents A1 OptiQ 4bit Parameters and Internals

LLM NameAgents A1 OptiQ 4bit
Repository 🤗https://huggingface.co/mlx-community/Agents-A1-OptiQ-4bit 
Base Model(s)  InternScience/Agents-A1   InternScience/Agents-A1
Model Size34.7b
Required VRAM22.2 GB
Updated2026-08-08
Maintainermlx-community
Model Typeqwen3_5_moe
Model Files  5.2 GB: 1-of-5   5.3 GB: 2-of-5   5.4 GB: 3-of-5   5.2 GB: 4-of-5   1.1 GB: 5-of-5
Quantization Type4bit
Model ArchitectureQwen3_5MoeForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Agents A1 OptiQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...CybersecurityLLM V1.0 Mlx 4Bit0K / 19.5 GB77345
KAT Coder V2.5 Dev OptiQ 4bit0K / 21.9 GB1143
XYZ Aquila Mini OptiQ 4bit0K / 36.3 GB343
Affine 5dfqbbh8ev Sft0K / 69.3 GB3880
5eqdtdzqle Ckpt1000 M70K / 71.7 GB220
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Agents-A1-OptiQ-4bit.