Gemma 7B It AWQ is an open-source language model by casperhansen. Features: 7b LLM, VRAM: 7.2GB, Context: 8K, Quantized, LLM Explorer Score: 0.12.
4-bit Awq Conversational Endpoints compatible Gemma Quantized Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/casperhansen/gemma-7b-it-awq
Gemma 7B It 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)
Gemma 7B It AWQ Parameters and Internals
| LLM Name | Gemma 7B It AWQ |
| Repository 🤗 | https://huggingface.co/casperhansen/gemma-7b-it-awq |
| Model Size | 7b |
| Required VRAM | 7.2 GB |
| Updated | 2026-04-04 |
| Maintainer | casperhansen |
| Model Type | gemma |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Model Architecture | GemmaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.38.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Gemma 7B It AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Codegemma 7B AWQ | 8K / 7.2 GB | 6 | 0 |
| Gemma 1.1 7B It AWQ | 8K / 7.2 GB | 6 | 0 |
| SeaLLM 7B V2.5 AWQ | 8K / 7.2 GB | 29 | 2 |
| CodeGemma 7B AWQ | 8K / 7.2 GB | 5 | 0 |
| SeaLLM 7B V2.5 AWQ | 8K / 5.6 GB | 5 | 0 |
| Gemma Ko 7B AWQ | 8K / 5.6 GB | 12 | 0 |
| Codegemma 1.1 7B It AWQ | 8K / 7.2 GB | 6 | 0 |
| Gemma 7B AWQ | 8K / 7.2 GB | 16 | 0 |
| Gemma 7B It AWQ | 8K / 7.2 GB | 13 | 0 |
| ...t Cleaner Gemma 32k Merged 16b | 31K / 17.1 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than casperhansen/gemma-7b-it-awq .
Rank the Gemma 7B It 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a