LLM EXPLORER 62,857 MODELS INDEXED

Llm Jp 4.1 8B Thinking 4bit Mlx by masahiroid

By masahiroid · 220 downloads
HF Repo ↗ Copy URL

Llm Jp 4.1 8B Thinking 4bit Mlx is an open-source language model by masahiroid. Features: 8b LLM, VRAM: 4.8GB, Context: 64K, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  4-bit   4bit Base model:llm-jp/llm-jp-4.1-8... Base model:quantized:llm-jp/ll...   Conversational   En   Ja   Llama   Mlx   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/masahiroid/llm-jp-4.1-8b-thinking-4bit-mlx 

Llm Jp 4.1 8B Thinking 4bit Mlx Parameters and Internals

LLM NameLlm Jp 4.1 8B Thinking 4bit Mlx
Repository 🤗https://huggingface.co/masahiroid/llm-jp-4.1-8b-thinking-4bit-mlx 
Base Model(s)  llm-jp/llm-jp-4.1-8b-thinking   llm-jp/llm-jp-4.1-8b-thinking
Model Size8b
Required VRAM4.8 GB
Updated2026-10-03
Maintainermasahiroid
Model Typellama
Model Files  4.8 GB
Supported Languagesen ja
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.51.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Vocabulary Size196608
Torch Data Typebfloat16

Best Alternatives to Llm Jp 4.1 8B Thinking 4bit Mlx

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB102
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB111
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB22
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB50
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB52525
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB21317
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB23
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB111
...B Instruct 262k V2 EXL2 5.0bpw256K / 5.8 GB51