Arxiv:2401.10491 Arxiv:2408.07990 Arxiv:2412.03187 4-bit Autotrain compatible Awq Base model:fuseai/fuseo1-deeps... Base model:quantized:fuseai/fu... Conversational Endpoints compatible Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Valdemardi/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-AWQ
FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview AWQ 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)
FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview AWQ Parameters and Internals
| LLM Name | FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview AWQ |
| Repository 🤗 | https://huggingface.co/Valdemardi/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-AWQ |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 19.4 GB |
| Updated | 2025-05-21 |
| Maintainer | Valdemardi |
| Model Type | qwen2 |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | Qwen2ForCausalLM |
| License | apache-2.0 |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.47.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| QwQ 32B AWQ | 128K / 19.4 GB | 61756 | 124 |
| ...epSeek R1 Distill Qwen 32B AWQ | 128K / 19.4 GB | 3051 | 32 |
| Openhands Lm 32B V0.1 AWQ | 32K / 19.4 GB | 3655 | 9 |
| Qwen2.5 32B Instruct AWQ | 32K / 19.4 GB | 51589 | 77 |
| Qwen2.5 Coder 32B Instruct AWQ | 32K / 19.4 GB | 9600 | 28 |
| QwQ 32B Preview AWQ | 32K / 19.4 GB | 670 | 25 |
| Qwen1.5 32B Chat AWQ | 32K / 21.2 GB | 41 | 18 |
| ...pSeek R1 Distill Qwen 32B 4bit | 128K / 18.5 GB | 50672 | 41 |
| QwQ 32B Unsloth Bnb 4bit | 128K / 22.5 GB | 7720 | 45 |
| ...k R1 Distill Qwen 32B Bnb 4bit | 128K / 19.2 GB | 7993 | 24 |
Note: green Score (e.g. "73.2") means that the model is better than Valdemardi/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview-AWQ .
Rank the FuseO1 DeepSeekR1 QwQ SkyT1 32B Preview AWQ 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? 47473 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227