Model Card on HF 🤗: https://huggingface.co/4bit/llava-v1.5-7b-5GB
Llava V1.5 7B 5GB 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 V1.5 7B 5GB Parameters and Internals
| LLM Name | Llava V1.5 7B 5GB |
| Repository 🤗 | https://huggingface.co/4bit/llava-v1.5-7b-5GB |
| Model Size | 7b |
| Required VRAM | 14.1 GB |
| Updated | 2025-08-23 |
| Maintainer | 4bit |
| Model Type | llava |
| Model Files | |
| Model Architecture | LlavaLlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.31.0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Llava V1.5 7B 5GB
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llava Merged Finetuned 7b | 32K / 15.1 GB | 1 | 1 |
| Llava V1.6 Mistral 7B PATCHED | 32K / 15.1 GB | 12 | 8 |
| KoLLaVA V1.5 Synatra 7B | 32K / 15.1 GB | 24 | 8 |
| Llava V1.5 7B | 4K / 13.5 GB | 1525979 | 487 |
| Llava V1.6 Vicuna 7B | 4K / 14.1 GB | 19368 | 131 |
| LLaVA NeXT Video 7B DPO | 4K / 14.2 GB | 7874 | 28 |
| Table Llava V1.5 7B | 4K / 14.2 GB | 16 | 13 |
| Vlm Rlaif Video Llava 7b | 4K / 14.2 GB | 5 | 0 |
| Open Llava Next Vicuna 7B | 4K / 14.7 GB | 187 | 3 |
| ...va 1.5 Image Classification V3 | 4K / 23.3 GB | 7 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than 4bit/llava-v1.5-7b-5GB .
Rank the Llava V1.5 7B 5GB 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? 50856 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124