MA
Meta AI
Multimodal model · United States ·Sep 2024

Llama 3.2 11B

Multimodal Open (Restricted)
10.6B
Parameters
6
Benchmarks

About Llama 3.2 11B

Llama 3.2 11B is an AI model developed by Meta AI, in the multimodal category, released in 2024, made available as an open-weights model with 10.6B params.

On this page you'll find Llama 3.2 11B's full specifications, including 6 benchmark results. Review provider pricing and benchmark scores below, or compare Llama 3.2 11B head-to-head with other multimodal models.

→ More models by Meta AI → All multimodal models → AI benchmarks leaderboard

Links

Announcement ↗

Run Llama 3.2 11B locally — what to buy

Share this build ↗

Sized to what Llama 3.2 11B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Good
Intel Arc B580 12GB
Consumer GPU · ~$249
~55.3 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Better
Intel Arc A770 16GB
Consumer GPU · ~$329
~67.9 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →
Best
NVIDIA GeForce RTX 5070 Ti
Consumer GPU · ~$749
~120 tok/s
Q4 · fits full context · up to 8k ctx
Runs with: ExLlamaV2, KoboldCpp, LM Studio
See full estimate →

Software support

·ExLlamaV2 ·KoboldCpp ·LM Studio ·MLX ·Ollama ·SGLang ·TensorRT-LLM ·llama.cpp ·vLLM ?KTransformers ?text-generation-webui

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Consumer GPU
27.2–120+ tok/s
28 options →
Apple
41.4–110.5 tok/s
17 options →
Datacenter GPU
112.1–120+ tok/s
13 options →

Community

Would you run Llama 3.2 11B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Llama 3.2 11B benchmark scores▶
Compare on the benchmark table →
Benchmark Category Score Variant
MMLU general 69.4% 5-shot-cited-aria
MATH math 51.9% cited-aria
ChartQA multimodal 83.4% cited-aria
DocVQA multimodal 84.400 cited-aria
MMMU multimodal 50.7% cited-aria
MathVista multimodal 51.5% cited-aria

More models like Llama 3.2 11B

AI
NeuroChess
· 72.3K
 MA
Muse Spark
Meta AI
 MA
Llama 4 Scout + ScaleRL
Meta AI · 109B
 MA
Llama 4 Maverick
Meta AI · 400B
 MA
Llama 4 Scout
Meta AI · 109B
 MA
Llama 4 Behemoth (preview)
Meta AI · 2T

Frequently asked questions

What is Llama 3.2 11B? ▶

Llama 3.2 11B is an AI model developed by Meta AI, in the multimodal category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Llama 3.2 11B? ▶

Llama 3.2 11B was developed by Meta AI and released in 2024.

Is Llama 3.2 11B open source or proprietary? ▶

Llama 3.2 11B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Llama 3.2 11B cost? ▶

Pricing for Llama 3.2 11B depends on the provider. See the providers table on this page for the latest API rates.

How does Llama 3.2 11B perform on benchmarks? ▶

Llama 3.2 11B is benchmarked across 6 evaluations on GenAIList, including MMLU (69.4%). See the full benchmark table below and compare it with other models.

No videos yet. Know a good one? Add it below.

Know a great video about Llama 3.2 11B?