4-bit 6bit Base model:quantized:rednote-h... Base model:rednote-hilab/dots.... Chat Conversational Dots1 En Mlx Quantized Region:us Safetensors Sharded Tensorflow Zh
Model Card on HF 🤗: https://huggingface.co/mlx-community/dots.llm1.inst-mixed-4-6bit
Dots.llm1.inst Mixed 4 6bit 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)
Dots.llm1.inst Mixed 4 6bit Parameters and Internals
| LLM Name | Dots.llm1.inst Mixed 4 6bit |
| Repository 🤗 | https://huggingface.co/mlx-community/dots.llm1.inst-mixed-4-6bit |
| Base Model(s) | |
| Model Size | 142.8b |
| Required VRAM | 86 GB |
| Updated | 2025-09-23 |
| Maintainer | mlx-community |
| Model Type | dots1 |
| Model Files | |
| Supported Languages | en zh |
| Quantization Type | 6bit |
| Model Architecture | Dots1ForCausalLM |
| License | mit |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.46.3 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endofresponse|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Dots.llm1.inst Mixed 4 6bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Dots.llm1.inst | 32K / 172 GB | 12743 | 167 |
| Dots.llm1.base | 32K / 176.3 GB | 40 | 61 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/dots.llm1.inst-mixed-4-6bit .
Rank the Dots.llm1.inst Mixed 4 6bit 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? 51557 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124