4-bit 4bit Autotrain compatible Base model:quantized:sm54/qwq-... Base model:sm54/qwq-deepseek-r... Conversational Endpoints compatible Merge Mergekit Mlx Mlx-my-repo Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit
QwQ DeepSeek R1 SkyT1 Flash Lightest 32B Mlx 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)
QwQ DeepSeek R1 SkyT1 Flash Lightest 32B Mlx 4Bit Parameters and Internals
| LLM Name | QwQ DeepSeek R1 SkyT1 Flash Lightest 32B Mlx 4Bit |
| Repository 🤗 | https://huggingface.co/mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 18.5 GB |
| Updated | 2025-04-26 |
| Maintainer | mlx-community |
| Model Type | qwen2 |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.43.1 |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to QwQ DeepSeek R1 SkyT1 Flash Lightest 32B Mlx 4Bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| QwQ 32B Unsloth Bnb 4bit | 128K / 22.5 GB | 24095 | 44 |
| ...pSeek R1 Distill Qwen 32B 4bit | 128K / 18.5 GB | 74621 | 40 |
| ...k R1 Distill Qwen 32B Bnb 4bit | 128K / 19.2 GB | 21626 | 24 |
| QwQ 32B 4bit | 128K / 18.5 GB | 1380 | 35 |
| QwQ 32B Bnb 4bit | 128K / 19.2 GB | 2712 | 3 |
| ...Q 32B Gptqmodel 4bit Vortex V1 | 128K / 21.3 GB | 1460 | 12 |
| ...ogito V1 Preview Qwen 32B 4bit | 128K / 18.5 GB | 230 | 5 |
| QwQ 32B 8bit | 128K / 34.9 GB | 769 | 13 |
| ...till Qwen 32B Unsloth Bnb 4bit | 128K / 35.6 GB | 1377 | 9 |
| QwQ 32B 6bit | 128K / 26.7 GB | 186 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/QwQ-DeepSeek-R1-SkyT1-Flash-Lightest-32B-mlx-4Bit .
Rank the QwQ DeepSeek R1 SkyT1 Flash Lightest 32B Mlx 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? 46715 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227