Llama-Mobile: 2.7-Bit Quantization Shrinks Llama 3.2 Vision 11B to 3.7GB for Phones
Luka Ribar · hf · 2026-08-24
Llama-Mobile is a quantization framework for deploying vision-language models on mobile.
- It uses a 2.7-bit format trained with self-generated data, requiring no human annotation.
- It compresses Llama 3.2 11B Vision Instruct to 3.7 GB while largely preserving visual question answering performance.
More from Infra
- SK Hynix ties new US plant to looser chip equipment exports to China, sources say — pstAsiatech · 2026-10-15
- Perplexity's new embedding models: index with a 9B model, search with 0.6B — antoine_chaffin · 2026-10-15
- Unsloth ships GGUF quants for Nemotron 3.5: Bolt-74B runs in 24GB RAM — danielhanchen · 2026-10-15
- vLLM-Omni ships Day-0 serving for FLUX 3 Image Klein with BF16, FP8, NVFP4 support — vllm_project · 2026-10-15
- NVIDIA's Nemotron 3.5 Super VL lands training and inference support on Applied Compute — ypatil125 · 2026-10-15
- CoreWeave bond yield tops 16% as loans outlast customer contracts by ~2 years — tengyanAI · 2026-10-15