4-bit Autotrain compatible Awq Conversational Endpoints compatible Quantized Qwen2 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Ichigo2899/arcee-ai-Arcee-Spark-AWQ
Arcee Ai Arcee Spark 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)
Arcee Ai Arcee Spark AWQ Parameters and Internals
| LLM Name | Arcee Ai Arcee Spark AWQ |
| Repository 🤗 | https://huggingface.co/Ichigo2899/arcee-ai-Arcee-Spark-AWQ |
| Model Size | 2b |
| Required VRAM | 5.6 GB |
| Updated | 2025-09-23 |
| Maintainer | Ichigo2899 |
| Model Type | qwen2 |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.42.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to Arcee Ai Arcee Spark AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek Qwen Modelstock 2B | 128K / 3.5 GB | 6 | 0 |
| OpenRHO 2B Thinker | 128K / 3.5 GB | 3 | 2 |
| Qwen2 2B Dolphin Hercules | 128K / 4.3 GB | 6 | 0 |
| Qwen2 2B RepleteCoder Upscaled | 128K / 4.3 GB | 5 | 0 |
| Qwen2 2B Dolphin RepleteCoder | 128K / 4.3 GB | 5 | 0 |
| Qwen2 2B RepleteCoder Hercules | 128K / 4.3 GB | 5 | 0 |
| Qwen2.5 2B Instruct | 32K / 5.9 GB | 11 | 1 |
| Carrot Ko 2B Instruct | 32K / 4.2 GB | 10 | 1 |
| Qwen2 Math 2B Instruct | 4K / 4.3 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Ichigo2899/arcee-ai-Arcee-Spark-AWQ .
Rank the Arcee Ai Arcee Spark 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124