4-bit Autotrain compatible Awq Base model:delcos/velara Base model:quantized:delcos/ve... Conversational En Llama2 Mistral Quantized Region:us Safetensors Starling
Model Card on HF 🤗: https://huggingface.co/TheBloke/Velara-AWQ
Velara 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)
Velara AWQ Parameters and Internals
| Model Type |
| |||||||||
| Use Cases |
| |||||||||
| Additional Notes |
| |||||||||
| Supported Languages |
| |||||||||
| Input Output |
|
| LLM Name | Velara AWQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Velara-AWQ |
| Model Name | Velara |
| Model Creator | Devon M |
| Base Model(s) | |
| Model Size | 1.8b |
| Required VRAM | 6.3 GB |
| Updated | 2025-09-21 |
| Maintainer | TheBloke |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | MistralForCausalLM |
| License | cc-by-nc-nd-4.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|im_end|> |
| Vocabulary Size | 32002 |
| Torch Data Type | float16 |
Best Alternatives to Velara AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| H2o Danube2 1.8B Chat MLX 4bit | 8K / 1.1 GB | 4 | 1 |
| Velara GPTQ | 32K / 6.3 GB | 6 | 1 |
| H2o Danube 1.8B Chat | 16K / 3.7 GB | 104 | 54 |
| H2o Danube 1.8B Base | 16K / 3.7 GB | 109 | 43 |
| Cypher Mini 1.8B | 16K / 3.7 GB | 6 | 2 |
| H2o Danube 1.8B Sft | 16K / 3.7 GB | 92 | 11 |
| PixieZehirNano | 16K / 3.7 GB | 10 | 0 |
| Cypher CoT 1.8B | 16K / 3.7 GB | 6 | 1 |
| ...1.8B Chat Sft Merge Fourier V1 | 16K / 7.3 GB | 4 | 1 |
| H2o Danube2 1.8B Chat | 8K / 3.7 GB | 518 | 61 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Velara-AWQ .
Rank the Velara 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? 51507 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124