LLM EXPLORER 67,952 MODELS INDEXED

Jev Omni MLX 4bit by Ruiruiz30

By Ruiruiz30 · 336 downloads

Jev Omni MLX 4bit is an open-source language model by Ruiruiz30. Features: 12b LLM, VRAM: 0.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.

  4-bit   4bit   Apple-silicon   Base model:akhilaaa3/jev-omni Base model:quantized:akhilaaa3...   Conversational   Gemma4 unified   Image-classification   Image-text-to-text   Mlx   Multimodal   Quantized   Region:us   Safetensors   Typed-decision

Jev Omni MLX 4bit Parameters and Internals

LLM NameJev Omni MLX 4bit
Repository πŸ€—https://huggingface.co/Ruiruiz30/Jev-Omni-MLX-4bit 
Base Model(s)  Jev Omni   akhilaaa3/Jev-Omni
Model Size12b
Required VRAM0.4 GB
Updated2026-09-26
MaintainerRuiruiz30
Model Typegemma4_unified
Model Files  0.6 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB   0.4 GB
Quantization Type4bit
Model ArchitectureGemma4UnifiedForConditionalGeneration
Licenseapache-2.0
Transformers Version5.10.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Jev Omni MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 12B It Qat W4a16 Ct0K / 10.3 GB156484556
... 4 12B It Qat Q4 0 Unquantized0K / 23.9 GB53198173
Gemma 4 12B It Qat 4bit0K / 10.9 GB1633825
... Coder Fable5 Composer2.5 8bit0K / 12.6 GB891735
... Coder Fable5 Composer2.5 4bit0K / 6.7 GB811138
Gemma 4 12B It OptiQ 4bit0K / 8.8 GB943841
Humanizerth Thai 12B Q8 0 MLX0K / 12.6 GB5402
Gemma 4 12B It 8bit0K / 12.7 GB570241
Gemma 4 12B It 4bit0K / 10.9 GB795315
Humanizerth Thai 12B Q4 0 MLX0K / 6.7 GB3873
Note: green Score (e.g. "73.2") means that the model is better than Ruiruiz30/Jev-Omni-MLX-4bit.