Qwen3.6 35B A3B MTP 5bit is an open-source language model by mlx-community. Features: 35b LLM, VRAM: 0.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.34.
5-bit 5bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.6-35b-a3... Conversational Draft-model En Mlx Mlx-vlm Moe Mtp Quantized Qwen Qwen3.6 Qwen3.6-35b-a3b Qwen3 5 mtp Region:us Safetensors Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-MTP-5bit
Qwen3.6 35B A3B MTP 5bit 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)
Qwen3.6 35B A3B MTP 5bit Parameters and Internals
| LLM Name | Qwen3.6 35B A3B MTP 5bit |
| Repository 🤗 | https://huggingface.co/mlx-community/Qwen3.6-35B-A3B-MTP-5bit |
| Base Model(s) | |
| Model Size | 35b |
| Required VRAM | 0.6 GB |
| Updated | 2026-06-03 |
| Maintainer | mlx-community |
| Model Type | qwen3_5_mtp |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 5bit |
| License | apache-2.0 |
| Model Max Length | 262144 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Errors | replace |
Rank the Qwen3.6 35B A3B MTP 5bit 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? 54253 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