LLM EXPLORER 65,418 MODELS INDEXED

Humanizerth Thai 12B Q8 0 MLX by chantra

By chantra · 540 downloads
HF Repo ↗ Copy URL

Humanizerth Thai 12B Q8 0 MLX is an open-source language model by chantra. Features: 12b LLM, VRAM: 12.6GB, License: gemma, Quantized, LLM Explorer Score: 0.32.

  8-bit   8bit   Base model:google/gemma-4-12b Base model:quantized:google/ge...   Content-creator   Conversational   Dataset:pantip qa   Dataset:wisesight sentiment   Dataset:wongnai reviews   De-ai   En   Gemma   Gemma-4   Gemma4   Humanizer   Mlx   Q8   Q8 0   Quantized   Region:us   Safetensors   Sharded   Social-media   Tensorflow   Th   Thai
Model Card on HF 🤗: https://huggingface.co/chantra/humanizerth-thai-12B-Q8_0-MLX 

Humanizerth Thai 12B Q8 0 MLX Parameters and Internals

LLM NameHumanizerth Thai 12B Q8 0 MLX
Repository 🤗https://huggingface.co/chantra/humanizerth-thai-12B-Q8_0-MLX 
Base Model(s)  Humanizer   Gemma 4 12B   jialinyyzz/humanizer   google/gemma-4-12B
Model Size12b
Required VRAM12.6 GB
Updated2026-10-22
Maintainerchantra
Model Typegemma4
Model Files  5.3 GB: 1-of-3   5.4 GB: 2-of-3   1.9 GB: 3-of-3
Supported Languagesth en
Quantization Typeq8|q8_0
Model ArchitectureGemma4UnifiedForConditionalGeneration
Licensegemma
Transformers Version5.14.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Humanizerth Thai 12B Q8 0 MLX

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
Humanizerth Thai 12B Q4 0 MLX0K / 6.7 GB3873
Humanizer 12B OptiQ 4bit0K / 8.8 GB2714
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
Gemma 4 12B It 8bit0K / 12.7 GB570241
Gemma 4 12B It 4bit0K / 10.9 GB795315
Note: green Score (e.g. "73.2") means that the model is better than chantra/humanizerth-thai-12B-Q8_0-MLX.