LLM EXPLORER 58,133 MODELS INDEXED

Qwen3.6 27B Int4 AutoRound by Lorbus

By Lorbus · 926139 downloads
HF Repo ↗ Copy URL

Qwen3.6 27B Int4 AutoRound is an open-source language model by Lorbus. Features: 27b LLM, VRAM: 18.4GB, License: apache-2.0, LLM Explorer Score: 0.38.

  Arxiv:2309.05516   4-bit   Auto-round   Autoround Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.6-27b   Conversational   Endpoints compatible   Image-text-to-text   Int4   Mtp   Multimodal   Quantization   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Vllm   W4a16   W4g128
Model Card on HF 🤗: https://huggingface.co/Lorbus/Qwen3.6-27B-int4-AutoRound 

Qwen3.6 27B Int4 AutoRound Parameters and Internals

LLM NameQwen3.6 27B Int4 AutoRound
Repository 🤗https://huggingface.co/Lorbus/Qwen3.6-27B-int4-AutoRound 
Base Model(s)  Qwen/Qwen3.6-27B   Qwen/Qwen3.6-27B
Model Size27b
Required VRAM18.4 GB
Updated2026-08-09
MaintainerLorbus
Model Typeqwen3_5
Model Files  2.1 GB: 1-of-10   2.1 GB: 2-of-10   2.1 GB: 3-of-10   2.1 GB: 4-of-10   2.1 GB: 5-of-10   2.1 GB: 6-of-10   0.8 GB: 7-of-10   2.5 GB: 8-of-10   0.0 GB: 9-of-10   2.5 GB: 10-of-10   0.3 GB
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.5.4
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 27B Int4 AutoRound

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.6 27B NVFP40K / 22 GB1887525419
ThinkingCap Qwen3.6 27B0K / 54.7 GB35947614
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
...e 4.6 Opus Reasoning Distilled0K / 55.2 GB632342928
Qwen3.5 27B0K / 55.2 GB811516
Fara1.5 27B0K / 54.8 GB3435281
ThinkingCap Qwen3.6 27B NVFP40K / 19.8 GB6318413
Qwen3.6 27B NVFP40K / 26.4 GB1279926103
Note: green Score (e.g. "73.2") means that the model is better than Lorbus/Qwen3.6-27B-int4-AutoRound.