Skip to content

Meta · Chat

Llama 3.2 3B

Meta 🇺🇸ChatLlama familyOpen weights. One of its sources says the weights are publicly available.
From Venice's listing:
Llama 3.2 3B is a lightweight model from Meta's Llama 3.2 family, sized for fast, low-cost tasks such as summarization, classification and rewriting. It supports text input and output with a 128K-token context window and handles several languages.
llminfo IQ
86.5
Market median price
$0.12 blended / 1M
Max context
131K
Listings
35

Evidence and sources

🤗 meta-llama/Llama-3.2-3B-Instruct Model architecture, as its sources state it llminfo IQ 86.5, ranked among chat models. From 255 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 75.7, 95% interval 62–89. From 3 benchmark families across 3 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (44.3). Costs more per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 18 Sep 2024Maker HQ: US (according to Meta's own website)
Sources: Together AI data, Venice.ai data, Models.dev data, Morpheus Inference Marketplace data, Hugging FacePrimary data from Together AI from Venice.ai: name, description from Models.dev: weights availability from Morpheus Inference Marketplace: architecture from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 6 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 4 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured outputPrompt cachingWeb search

Listings

 Flowdotmeta-llama/llama-3.2-3b-instruct:free · freeSource: FlowDot data131K$0.00$0.00
 OpenRoutermeta-llama/llama-3.2-3b-instruct:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00
 Lambda AIlambda_ai/llama3.2-3b-instructSource: LiteLLM data131K$0.015$0.025
 Aihubmixmeta-llama/llama-3.2-3b-instruct:free · freeSource: AIHubMix data docsNot published by the provider$0.02$0.02
 Eden AIInference by DeepInfradeepinfra/meta-llama/Llama-3.2-3B-InstructSource: Models.dev data131K$0.02$0.02
 DeepInfradeepinfra/meta-llama/Llama-3.2-3B-InstructSource: LiteLLM data131K$0.02$0.02
 Inference Netllama-3.2-3b-instructSources: Inference.net data, Models.dev data16K$0.02$0.02
 NanoGPTInference by KitaniRegions: GLBmeta-llama/llama-3.2-3b-instruct · int4Source: NanoGPTNot published by the provider$0.0289cache read $0.0145$0.0466
 Novita AImeta-llama/llama-3.2-3b-instructSources: GenAI Prices data, LiteLLM data33K$0.03$0.05
 Llamagatellamagate/llama-3.2-3bSource: LiteLLM data131K$0.04$0.08
Show all 30 listings

Showing 10 of 30: the cheapest per 1M input tokens from each provider.

Also sold by Cloudflare Workers AI, Featherless AI, Fireworks AI, Hugging Face, Hyperbolic, Kilo, Parasail, Snowflake, Together AI, Venice, Vercel, Vercel AI Gateway, Watsonx.

5 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Multilingual

SeaLLMs SeaExamSource: SeaLLMs Leaderboard for SEA Languages data docs

Reasoning

Instruction following

Knowledge

Math

Science

Other

Data credits: CSEBenchmark (Wang et al., IEEE S&P 2025). Copyright (c) 2024 NASP. MIT License. (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated.

Also known as: @cf/meta/llama-3.2-3b-instruct, cloudflare/@cf/meta/llama-3.2-3b-instruct, deepinfra/meta-llama/llama-3.2-3b-instruct, fireworks_ai/accounts/fireworks/models/llama-v3p2-3b, fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct, hyperbolic/meta-llama/llama-3.2-3b-instruct, lambda_ai/llama3.2-3b-instruct, llama 3.2 3b, llama-3.2-3b-instruct, llama-3.2-3b:web, llama3.2:3b, llamagate/llama-3.2-3b, meta-llama/llama-3.2-3b, meta-llama/llama-3.2-3b-instruct, meta-llama/llama-3.2-3b-instruct:free, meta/llama-3-2-3b, meta/llama-3.2-3b, meta/llama-3.2-3b-instruct, novita/meta-llama/llama-3.2-3b-instruct, parasail-llama-32-3b-instruct, snowflake/llama3.2-3b, together_ai/meta-llama/llama-3.2-3b-instruct, vercel_ai_gateway/meta/llama-3.2-3b, watsonx/meta-llama/llama-3-2-3b-instruct

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works