# Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs

arXiv: https://arxiv.org/abs/2608.21134 · HTML: https://mlsanity.com/paper/2608.21134/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)

## Builds on (most cited first, 28 of 28)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [InfographicVQA](https://mlsanity.com/paper/2104.12756/) (2021)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [Extreme Compression of Large Language Models via Additive Quantization](https://mlsanity.com/paper/2401.06118/) (2024)
- [Microscaling Data Formats for Deep Learning](https://mlsanity.com/paper/2310.10537/) (2023)
- [Q-VLM: Post-training Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2410.08119/) (2024)
- [MBQ: Modality-Balanced Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2412.19509/) (2024)
- [Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery](https://mlsanity.com/paper/2601.20088/) (2026)
- [NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache](https://mlsanity.com/paper/2505.18231/) (2025)
- [Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs](https://mlsanity.com/paper/2501.00032/) (2024)
- [Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification](https://mlsanity.com/paper/2601.07892/) (2026)
- [Optimal Formats for Weight Quantisation](https://mlsanity.com/paper/2505.12988/) (2025)

## Abstract (arXiv)

Deploying vision-language models (VLMs) on mobile devices is challenging due to their significant memory and compute requirements. We present a framework for quantizing VLMs for efficient inference on resource-constrained hardware. Our approach combines a quantization pipeline that uses the model itself to generate training data and does not require access to the training setup, with a novel 2.7-bit-per-parameter format supporting efficient execution on Arm CPUs. We validate our approach by compressing the Llama 3.2 11B Vision Instruct model to 3.7 GB with 8-bit activations, preserving strong performance on a set of standard visual question answering tasks.