LLM EXPLORER 63,791 MODELS INDEXED

D1 3B MLX 8bit by DJLougen

By DJLougen · 210 downloads
HF Repo ↗ Copy URL

D1 3B MLX 8bit is an open-source language model by DJLougen. Features: 3b LLM, VRAM: 3.7GB, License: other, Quantized, LLM Explorer Score: 0.32.

  8-bit   8bit   Ar   Base model:liquidai/d1-3b Base model:quantized:liquidai/...   Calibration   Classification   Conversational   Custom code   De   Decision   Edge   En   Es   Fr   Hi   Id   Image-text-to-text   It   Ja   Ko   Lfm2   Lfm2-vl   Lfm2.5   Lfm2 vl   Mlx   Mlx-vlm   Pl   Pt   Quantized   Region:us   Ru   Safetensors   System-one   Th   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/DJLougen/d1-3B-MLX-8bit 

D1 3B MLX 8bit Parameters and Internals

LLM NameD1 3B MLX 8bit
Repository 🤗https://huggingface.co/DJLougen/d1-3B-MLX-8bit 
Base Model(s)  D1 3B   LiquidAI/d1-3B
Model Size3b
Required VRAM3.7 GB
Updated2026-10-11
MaintainerDJLougen
Model Typelfm2_vl
Model Files  3.7 GB
Supported Languagesar zh en fr de hi id it ja ko pl pt ru es th vi
Quantization Type8bit
Model ArchitectureLfm2VlForConditionalGeneration
Licenseother
Transformers Version5.14.1
Tokenizer ClassTokenizersBackend
Padding Token<|pad|>

Best Alternatives to D1 3B MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 VL 3B OptiQ 4bit0K / 2 GB13271
LFM2.5 VL 3B MLX 8bit0K / 3.7 GB32413
LFM2.5 VL 3B MLX 4bit0K / 2.4 GB27215
LFM2.5 VL 3B MLX 6bit0K / 3 GB8312
LFM2.5 VL 3B MLX 5bit0K / 2.7 GB5912
LFM2 VL 3B 4bit0K / 2.3 GB2964
LFM2 VL 3B 8bit0K / 3.6 GB254
LFM2 VL 3B 5bit0K / 2.6 GB141
D1 3B0K / 6.2 GB9088260
D1 3B W8a80K / 3.8 GB1516
Note: green Score (e.g. "73.2") means that the model is better than DJLougen/d1-3B-MLX-8bit.