LLM EXPLORER 62,751 MODELS INDEXED

Tiny Pickle V3 Coder 4bit by mlx-community

By mlx-community · 95 downloads

Tiny Pickle V3 Coder 4bit is an open-source language model by mlx-community. Features: 4.8b LLM, VRAM: 17.2GB, Context: 256K, License: apache-2.0, Quantized, Code Generating, LLM Explorer Score: 0.26.

  4-bit   4bit   Apple-silicon Base model:quantized:vsan/tiny... Base model:vsan/tiny-pickle-v3...   Codegen   Coding   Conversational   Mlx   Moe   Quantized   Qwen3-coder   Qwen3 moe   Region:us   Safetensors   Sharded   Software-engineering   Tensorflow   Tiny-pickle

Tiny Pickle V3 Coder 4bit Parameters and Internals

LLM NameTiny Pickle V3 Coder 4bit
Repository πŸ€—https://huggingface.co/mlx-community/Tiny-Pickle-v3-Coder-4bit 
Base Model(s)  Tiny Pickle V3 Coder   vsan/tiny-pickle-v3-coder
Model Size4.8b
Required VRAM17.2 GB
Updated2026-08-26
Maintainermlx-community
Model Typeqwen3_moe
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   5.3 GB: 3-of-4   1.2 GB: 4-of-4
Quantization Type4bit
Generates CodeYes
Model ArchitectureQwen3MoeForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace