LLM EXPLORER 59,358 MODELS INDEXED

Distill 1.7B 4bit MLX by samuelfaj

By samuelfaj · 179 downloads
HF Repo ↗ Copy URL

Distill 1.7B 4bit MLX is an open-source language model by samuelfaj. Features: 1.7b LLM, VRAM: 1.1GB, Context: 40K, License: apache-2.0, Quantized, LLM Explorer Score: 0.25.

  4-bit   4bit Base model:quantized:samuelfaj... Base model:samuelfaj/distill-1...   Cli   Code   Conversational   Distill   Domain-specific   Expert-model   Mlx   Quantized   Qwen   Qwen3   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/samuelfaj/distill-1.7B-4bit-MLX 

Distill 1.7B 4bit MLX Parameters and Internals

LLM NameDistill 1.7B 4bit MLX
Repository 🤗https://huggingface.co/samuelfaj/distill-1.7B-4bit-MLX 
Base Model(s)  samuelfaj/distill-1.7B-MLX   samuelfaj/distill-1.7B-MLX
Model Size1.7b
Required VRAM1.1 GB
Updated2026-07-10
Maintainersamuelfaj
Model Typeqwen3
Model Files  1.1 GB
Quantization Type4bit
Model ArchitectureQwen3ForCausalLM
Licenseapache-2.0
Context Length40960
Model Max Length40960
Transformers Version4.51.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Distill 1.7B 4bit MLX

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3 1.7B MLX 4bit64K / 0.9 GB8684
Unsloth Qwen3 1.7B Finetune V140K / 3.4 GB2810
Qwen3 1.7B Unsloth Bnb 4bit40K / 1.4 GB5371012
Qwen3 1.7B 4bit40K / 1 GB140826
Qwen3 1.7B Bnb 4bit40K / 1.4 GB32275
Qwen3 1.7B 4bit DWQ 05312540K / 1 GB5962
Qwen3 1.7B MLX 8bit40K / 1.8 GB6103
...Qwen3 1.7B Abliterated V1 4bit40K / 1 GB8623
...wen3 1.7B Tamil 16bit Instruct40K / 3.4 GB130
Qwen3 1.7B MLX 6bit40K / 1.3 GB1223
Note: green Score (e.g. "73.2") means that the model is better than samuelfaj/distill-1.7B-4bit-MLX.