MLX Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled 4bit is an open-source language model by Jackrong. Features: 27b LLM, VRAM: 15.1GB, License: lgpl-3.0, Quantized, LLM Explorer Score: 0.32.
4-bit 4bit Base model:jackrong/qwen3.5-27... Base model:quantized:jackrong/... Chain-of-thought Conversational Dense En Mlx Quantized Qwen Qwen3.5 Qwen3 5 Reasoning Region:us Safetensors Sharded Tensorflow Unsloth Zh
Model Card on HF 🤗: https://huggingface.co/Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-4bit
MLX Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled 4bit Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MLX Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled 4bit Parameters and Internals
| LLM Name | MLX Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled 4bit |
| Repository 🤗 | https://huggingface.co/Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-4bit |
| Base Model(s) | |
| Model Size | 27b |
| Required VRAM | 15.1 GB |
| Updated | 2026-04-08 |
| Maintainer | Jackrong |
| Model Type | qwen3_5 |
| Model Files | |
| Supported Languages | en zh |
| Quantization Type | 4bit |
| Model Architecture | Qwen3_5ForConditionalGeneration |
| License | lgpl-3.0 |
| Model Max Length | 262144 |
| Tokenizer Class | TokenizersBackend |
| Padding Token | <|endoftext|> |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to MLX Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen3.5 27B 4bit DWQ | 0K / 15.2 GB | 1418 | 5 |
| MLX Qwopus3.5 27B V3 6bit | 0K / 21.8 GB | 901 | 2 |
| ...e 4.6 Opus Reasoning Distilled | 0K / 55.2 GB | 253259 | 1532 |
| Qwen3.5 27B | 0K / 54.7 GB | 39083 | 13 |
| ....6 Opus Reasoning Distilled V2 | 0K / 55.2 GB | 10667 | 83 |
| Qwopus3.5 27B V3 HLWQ V7 GPTQ | 0K / 19.2 GB | 667 | 5 |
| Qwopus3.5 27B V3 | 0K / 54.7 GB | 30121 | 216 |
| ...s3.5 27B V3 PolarQuant V7 GPTQ | 0K / 19.2 GB | 302 | 3 |
| Qwen3.5 27B Anko | 0K / 54.7 GB | 82 | 5 |
| ...e 4.6 Opus Reasoning Distilled | 0K / 55.2 GB | 85 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-4bit .
Rank the MLX Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled 4bit Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52996 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a