Arxiv:1910.09700 4-bit Autotrain compatible Bitsandbytes Cohere Endpoints compatible Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/QuantiPhy/aya-23-8B-4bq
Aya 23 8B 4bq 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)
Aya 23 8B 4bq Parameters and Internals
| LLM Name | Aya 23 8B 4bq |
| Repository 🤗 | https://huggingface.co/QuantiPhy/aya-23-8B-4bq |
| Model Size | 8b |
| Required VRAM | 5.7 GB |
| Updated | 2025-06-10 |
| Maintainer | QuantiPhy |
| Model Type | cohere |
| Model Files | |
| Model Architecture | CohereForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.42.0.dev0 |
| Vocabulary Size | 256000 |
| Torch Data Type | bfloat16 |
Quantized Models of the Aya 23 8B 4bq
Model |
Likes |
Downloads |
VRAM |
|---|---|---|---|
| Aya 23 8B 4bit | 2 | 33 | 4 GB |
Best Alternatives to Aya 23 8B 4bq
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Aya Expanse 8B | 8K / 16 GB | 31951 | 359 |
| Aya Expanse 8B | 8K / 16 GB | 22267 | 376 |
| Aya Z | 8K / 16 GB | 486 | 1 |
| Aya Expanse 8B | 8K / 16 GB | 65 | 0 |
| Aya Medikal V2 | 8K / 16 GB | 516 | 1 |
| Us | 8K / 16 GB | 19 | 0 |
| Aya X Mod | 8K / 16 GB | 7 | 1 |
| Aya X Yeni | 8K / 16 GB | 8 | 0 |
| Aya Test Model V2 | 8K / 16 GB | 16 | 0 |
| Aya Expanse 8B Abliterated | 8K / 16 GB | 497 | 8 |
Note: green Score (e.g. "73.2") means that the model is better than QuantiPhy/aya-23-8B-4bq .
Rank the Aya 23 8B 4bq 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? 48075 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124