LLM EXPLORER 59,420 MODELS INDEXED

Claude Llama 8B Think Mlx 4Bit by mondk

By mondk · 279 downloads
HF Repo ↗ Copy URL

Claude Llama 8B Think Mlx 4Bit is an open-source language model by mondk. Features: 8b LLM, VRAM: 4.5GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.35.

  4-bit   4bit Base model:mondk/claude-llama-... Base model:quantized:mondk/cla...   Claude   Conversational Dataset:mondk/claude-sonnet5-j...   De   En   Es   Fr   It   Ja   Ko   Llama   Mlx   Mlx-my-repo   Pt   Quantized   Region:us   Ru   Safetensors   Thinking   Zh
Model Card on HF 🤗: https://huggingface.co/mondk/claude-llama-8B-think-mlx-4Bit 

Claude Llama 8B Think Mlx 4Bit Parameters and Internals

LLM NameClaude Llama 8B Think Mlx 4Bit
Repository 🤗https://huggingface.co/mondk/claude-llama-8B-think-mlx-4Bit 
Base Model(s)  Claude Llama 8B Think   mondk/claude-llama-8B-think
Model Size8b
Required VRAM4.5 GB
Updated2026-08-24
Maintainermondk
Model Typellama
Model Files  4.5 GB
Supported Languagesen fr de es it pt zh ja ru ko
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Tokenizer ClassTokenizersBackend
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Claude Llama 8B Think Mlx 4Bit

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