4-bit Awq Base model:mihaiii/metis-0.5 Base model:quantized:mihaiii/m... Custom code Mistral Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Metis-0.5-AWQ
Metis 0.5 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)
Metis 0.5 AWQ Parameters and Internals
| Model Type |
| |||
| Additional Notes |
| |||
| Input Output |
|
| LLM Name | Metis 0.5 AWQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Metis-0.5-AWQ |
| Model Name | Metis 0.5 |
| Model Creator | Mihai |
| Base Model(s) | |
| Model Size | 7.2b |
| Required VRAM | 4.2 GB |
| Updated | 2026-02-22 |
| Maintainer | TheBloke |
| Model Type | mistral |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Metis 0.5 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Hc Mistral Alpaca Merged AWQ | 32K / 4.2 GB | 9 | 0 |
| Phoenix AWQ | 32K / 4.2 GB | 13 | 1 |
| Mistral Ft Optimized 1227 AWQ | 32K / 4.2 GB | 5 | 1 |
| XDAN L1 Chat RL V1 AWQ | 32K / 4.2 GB | 6 | 1 |
| Apricot Wildflower 20 AWQ | 32K / 4.2 GB | 3 | 1 |
| OpenZephyrChat V0.2 AWQ | 32K / 4.2 GB | 8 | 3 |
| Ana V1 M7 AWQ | 32K / 4.2 GB | 1 | 2 |
| OpenZephyrChat AWQ | 32K / 4.2 GB | 4 | 2 |
| ...2.5 Neural Chat V3.3 Slerp AWQ | 32K / 4.2 GB | 2 | 1 |
| Tess XS V1.1 AWQ | 32K / 4.2 GB | 5 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Metis-0.5-AWQ .
Rank the Metis 0.5 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? 51611 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124