4-bit 4bit Autotrain compatible Base model:google/gemma-2-9b-i... Base model:quantized:google/ge... Conversational Gemma2 Gptq Instruct Quantized Region:us Safetensors Sharded Tensorflow
Gemma 2 9B Instruct 4Bit GPTQ 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 2 9B Instruct 4Bit GPTQ Parameters and Internals
| LLM Name | Gemma 2 9B Instruct 4Bit GPTQ |
| Repository 🤗 | https://huggingface.co/Granther/Gemma-2-9B-Instruct-4Bit-GPTQ |
| Model Name | Gemma-2-9B-Instruct-4Bit-GPTQ |
| Base Model(s) | |
| Model Size | 9b |
| Required VRAM | 6.2 GB |
| Updated | 2024-10-18 |
| Maintainer | Granther |
| Model Type | gemma2 |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | Gemma2ForCausalLM |
| License | gemma |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.43.0.dev0 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Gemma 2 9B Instruct 4Bit GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Odin 9B | 8K / 18.6 GB | 119 | 1 |
| SILMA 9B Instruct V1.0 | 8K / 18.6 GB | 5873 | 40 |
| ...B IT Simpo Infinity Preference | 8K / 18.6 GB | 2331 | 14 |
| RoGemma2 9B Instruct | 8K / GB | 95 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Granther/Gemma-2-9B-Instruct-4Bit-GPTQ .
Rank the Gemma 2 9B Instruct 4Bit GPTQ 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803