4-bit Abliterated Autotrain compatible Base model:huihui-ai/deepseek-... Base model:quantized:huihui-ai... Conversational Endpoints compatible Mlx Mlx-my-repo Q4 Quantized Qwen2 Region:us Safetensors Sharded Tensorflow Uncensored
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-Q4-mlx
DeepSeek R1 Distill Qwen 14B Abliterated V2 Q4 Mlx 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)
DeepSeek R1 Distill Qwen 14B Abliterated V2 Q4 Mlx Parameters and Internals
| LLM Name | DeepSeek R1 Distill Qwen 14B Abliterated V2 Q4 Mlx |
| Repository 🤗 | https://huggingface.co/mlx-community/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-Q4-mlx |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 8.3 GB |
| Updated | 2025-08-22 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Model Files | |
| Quantization Type | q4 |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to DeepSeek R1 Distill Qwen 14B Abliterated V2 Q4 Mlx
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 14B Instruct 1M 8bit | 986K / 15.7 GB | 32 | 7 |
| ...B Instruct 1M Unsloth Bnb 4bit | 986K / 14.3 GB | 15 | 4 |
| Qwen2.5 14B Instruct 1M 4bit | 986K / 8.3 GB | 22 | 2 |
| ...en2.5 14B Instruct 1M Bnb 4bit | 986K / 9.9 GB | 6 | 2 |
| QwQ 14B Math V0.2 | 128K / 29.7 GB | 147 | 15 |
| Qwen Carpmuscle V0.3 | 128K / 29.7 GB | 6 | 0 |
| DeepCoder 14B Preview 8bit | 128K / 15.7 GB | 1099 | 3 |
| DeepCoder 14B Preview 4bit | 128K / 8.3 GB | 1010 | 2 |
| ...till Qwen 14B Unsloth Bnb 4bit | 128K / 14.2 GB | 3465 | 29 |
| Qwen2.5 14B Unsloth Bnb 4bit | 128K / 12.1 GB | 2683 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-Q4-mlx .
Rank the DeepSeek R1 Distill Qwen 14B Abliterated V2 Q4 Mlx 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? 50804 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124