This is an MLX conversion of migtissera/Tess-4-27B, a Qwen3.6-27B based Qwen3.5-family multimodal reasoning model. Conversion Source model: migtissera/Tess-4-27B Source revision: 65e1463e388bd2e94afc33a7d376d501cebe71b2 Format: MLX safetensors Quantization: mixed 4 6 Reported size: about 16 GB Reported average precision: 5.092 bits per weight Vision tower: kept unquantized by the mlx-vlm...
Model source
Source description
Sources
1 sourceSource excerpts
3 excerptsThis is an MLX conversion of migtissera/Tess-4-27B, a Qwen3.6-27B based Qwen3.5-family multimodal reasoning model. Conversion Source model: migtissera/Tess-4-27B Source revision: 65e1463e388bd2e94afc33a7d376d501cebe71b2 Format: MLX safetensors Quantization:…
migtissera/Tess-4-27B65e1463e388bd2e94afc33a7d376d501cebe71b2mixed_4_6lm_headv_projdown_projmlx-vlmmlx-vlmbash pip install -U mlx mlx-lm pip install -U git+https://github.com/Blaizzy/mlx-vlm.git python from mlx_vlm.generate import generate from mlx_vlm.utils import load model_id = "ukint-vs/Tess-4-27B-MLX-mixed_4_6" model, processor = load(model_id) messages = [ {"role": "user", "content": "Explain the tradeoffs of LoRA vs full fine-tuning."} ] prompt = processor.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, ) response = generate( model, processor, prompt, max_tokens=512, temp=0.6, ) print(response.text) python prompt = processor.tokenizer.apply_chat_template( [{"role": "user", "content": "What is 2+2? Answer briefly."}], tokenize=False, add_generation_prompt=True, enable_thinking=False, ) text user Your prompt here assistant ... reasoning ... ... answer ... processor.tokenizer.apply_chat_template(...)text User: What is 2+2? Answer briefly. Assistant: 4 license: apache-2.0 basemodel: migtissera/Tess-4-27B Qwen/Qwen3.6-27B libraryname: mlx pipelinetag: image-text-to-text tags: mlx mlx-vlm qwen35 qwen3 qwen3.6 tess multimodal vision-language reasoning thinking long-context agentic tool-use
ukint-vs/Tess-4-27B-MLX-mixed_4_6