Model Card on HF 🤗: https://huggingface.co/panoyo9829/llava-1.6-gptq-4bit
Llava 1.6 Gptq 4bit 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)
Llava 1.6 Gptq 4bit Parameters and Internals
| LLM Name | Llava 1.6 Gptq 4bit |
| Repository 🤗 | https://huggingface.co/panoyo9829/llava-1.6-gptq-4bit |
| Model Size | 7b |
| Required VRAM | 6 GB |
| Updated | 2025-12-07 |
| Maintainer | panoyo9829 |
| Model Type | llava |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | LlavaLlamaForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Llava 1.6 Gptq 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llava 1.6 Gptq 8bit | 32K / 9.6 GB | 7 | 0 |
| Video LLaVA 7B GPTQ 4bit V1 | 4K / 5.3 GB | 5 | 0 |
| Video LLaVA 7B GPTQ 4bit V0 | 4K / 5.3 GB | 5 | 0 |
| ShareGPT4V 7B GPTQ | 4K / 3.9 GB | 0 | 3 |
| Llava Merged Finetuned 7b | 32K / 15.1 GB | 2 | 1 |
| Llava V1.6 Mistral 7B PATCHED | 32K / 15.1 GB | 5 | 8 |
| KoLLaVA V1.5 Synatra 7B | 32K / 15.1 GB | 78 | 8 |
| Llava V1.5 7B | 4K / 13.5 GB | 537166 | 494 |
| Llava V1.6 Vicuna 7B | 4K / 14.1 GB | 33429 | 141 |
| LLaVA NeXT Video 7B DPO | 4K / 14.2 GB | 3420 | 28 |
Note: green Score (e.g. "73.2") means that the model is better than panoyo9829/llava-1.6-gptq-4bit .
Rank the Llava 1.6 Gptq 4bit 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? 51557 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124