LLaVA Team
LLaVA 1.6 34B
Vision-language model. Analyze images and answer questions about them. Best quality variant.
34B parametersllavaapache-2.04K context22GB - 38GB VRAM
Check Your Hardware
See which quantizations of LLaVA 1.6 34B your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q4_K_M | 4.5 | 20 GB | 22 GB | 26 GB | 85% |
| Q8_0 | 8 | 36 GB | 38 GB | 42 GB | 98% |
Frequently Asked Questions
How much VRAM do I need to run LLaVA 1.6 34B?
LLaVA 1.6 34B requires 22GB VRAM minimum with Q4_K_M quantization. For full precision, you need 38GB VRAM.
What is the best quantization for LLaVA 1.6 34B?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.