LLM EXPLORER 58,873 MODELS INDEXED

Qwen3 Coder Next Int4 AutoRound by Intel

By Intel · 13678 downloads
HF Repo ↗ Copy URL

Qwen3 Coder Next Int4 AutoRound is an open-source language model by Intel. Features: 11.8b LLM, VRAM: 43.5GB, Context: 256K, Code Generating, LLM Explorer Score: 0.29.

  Arxiv:2309.05516   4-bit   Auto-round Base model:quantized:qwen/qwen... Base model:qwen/qwen3-coder-ne...   Codegen   Conversational   Qwen3 next   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Intel/Qwen3-Coder-Next-int4-AutoRound 

Qwen3 Coder Next Int4 AutoRound Parameters and Internals

LLM NameQwen3 Coder Next Int4 AutoRound
Repository 🤗https://huggingface.co/Intel/Qwen3-Coder-Next-int4-AutoRound 
Base Model(s)  Qwen3 Coder Next   Qwen/Qwen3-Coder-Next
Model Size11.8b
Required VRAM43.5 GB
Updated2026-08-04
MaintainerIntel
Model Typeqwen3_next
Model Files  4.3 GB: 1-of-11   4.3 GB: 2-of-11   4.3 GB: 3-of-11   4.3 GB: 4-of-11   4.3 GB: 5-of-11   4.3 GB: 6-of-11   4.3 GB: 7-of-11   4.3 GB: 8-of-11   4.3 GB: 9-of-11   3.0 GB: 10-of-11   1.8 GB: 11-of-11
Generates CodeYes
Model ArchitectureQwen3NextForCausalLM
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace