Llama 3.2 11B Vision Instruct

Source-available Meta · 2024-09-25 · Llama 3.2 Community License

Llama's first openly released vision-language checkpoint at small-medium scale, built by training a cross-attention adapter that integrates a pre-trained image encoder into the Llama 3.1 8B text backbone. The text-only behavior of the underlying language model is preserved so the model can substitute for the dense text checkpoint.

Cost

— / Mtok input

— / Mtok output

Together AI · as of 2026-05-19

via Artificial Analysis ↗

Architecture

Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture: dense
Total params: not disclosed
Active params: 10.6B
Context window: 131K tokens
Attention: gqa
Position encoding: rope-llama3
Training hardware: H100
Post-training: sft, rlhf
OSI-approved: no
Data released: no
Training code: not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

Available quantizations

GGUF llama.cpp's container; the common local format, k-quants from Q2 to Q8. runs on llama.cpp, Ollama

GPTQ Post-training 4-bit weight quantization for GPU serving. runs on vLLM, SGLang, Transformers

FP8 8-bit float, frequently a native release on Hopper / Blackwell GPUs. runs on vLLM, SGLang, TensorRT-LLM

bitsandbytes On-the-fly NF4 / INT8 weight quantization inside Transformers. runs on Transformers

Verified via the Hugging Face model tree ↗. Community quantizations change over time; the families shown are those with published weights at audit time.

Notable innovations