LLM EXPLORER 58,975 MODELS INDEXED

Qwen3.5 27B by unsloth

By unsloth · 8115 downloads
HF Repo ↗ Copy URL

Qwen3.5 27B is an open-source language model by unsloth. Features: 27b LLM, VRAM: 55.2GB, License: apache-2.0, LLM Explorer Score: 0.42, ELO: 1408.

Base model:finetune:qwen/qwen3...   Base model:qwen/qwen3.5-27b   Conversational   Image-text-to-text   Qwen3 5   Qwen3 5 moe   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen3.5-27B 

Qwen3.5 27B Benchmarks

LMSys ELO 1408 vs 1272 (so35) 10.7%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen3.5 27B Parameters and Internals

LLM NameQwen3.5 27B
Repository 🤗https://huggingface.co/unsloth/Qwen3.5-27B 
Base Model(s)  Qwen/Qwen3.5-27B   Qwen/Qwen3.5-27B
Model Size27b
Required VRAM55.2 GB
Updated2026-08-04
Maintainerunsloth
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-11   5.3 GB: 2-of-11   5.3 GB: 3-of-11   5.3 GB: 4-of-11   5.3 GB: 5-of-11   5.3 GB: 6-of-11   5.3 GB: 7-of-11   5.4 GB: 8-of-11   5.3 GB: 9-of-11   5.3 GB: 10-of-11   2.1 GB: 11-of-11
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3.5 27B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B NVFP40K / 22 GB1887525419
ThinkingCap Qwen3.6 27B0K / 54.7 GB35947614
Huihui Qwen3.8 27B Abliterated0K / 55.6 GB148576
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
...n3.8 27B MTPLX Optimized Speed0K / 19.6 GB698950
...e 4.6 Opus Reasoning Distilled0K / 55.2 GB632342928
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen3.5-27B.