Name: Llama 3.2 3B Instruct
Brand: Meta

Llama 3.2 3B Instruct is Meta's language model with a 131K context window and up to 118K output tokens, available from 11 providers, starting at $0.015 / 1M input and $0.02 / 1M output. Meta's 3B instruction-tuned LLM from Llama 3.2, providing efficient instruction-following for resource-constrained environments across multiple cloud regions.

Specifications
Canonical ID	`meta-llama-3-2-3b-instruct`
Type	Language
Status	Deprecated
Creator	Meta
Providers	Amazon Bedrock Cloudflare Workers AI DeepInfra Fireworks AI Hyperbolic IBM watsonx Lambda Novita OpenRouter SambaNova Together AI
Context Window	131K tokens
Max Output	118K tokens
Input Modalities	Text
Output Modalities	Text
Parameters	3B
HuggingFace Likes	2,113
HuggingFace Downloads (30d)	1,988,470
HuggingFace Downloads (all-time)	40,170,042
Release Date	2024-09-25 · 2 years ago
Knowledge Cutoff	2023-12-31 · 3 years ago
Deprecation Date	2025-06-25

Benchmarks
Intelligence Index	#478
Math Index	#261
MMLU-Pro	#325
GPQA	#520
HLE	#353
LiveCodeBench	#316
AIME	#142
IFBench	#389
Time to First Token	#202
SciCode	#501
MATH-500	#167
AIME 2025	#261
LCR	#406
TAU2	#331
Output TPS	#431

Capabilities

Input1/5

Text✓

Image·

Audio·

Video·

PDF·

Output1/5

Text✓

Image·

Audio·

Video·

Embedding·

Capabilities4/13

Reasoning·

Adaptive Reasoning·

Function Calling✓

Parallel Function Calling✓

Structured Outputs✓

Native JSON Schema✓

Web Search·

URL Context·

Computer Use·

Code Execution·

File Search·

Prompt Caching·

Assistant Prefill·

Pricing by Provider

US Dollar ($)

Per 1M tokens

Provider	Standard
Provider	Input $ / 1M	Output $ / 1M
Amazon Bedrock `meta.llama3-2-3b-instruct-v1:0`	$0.15	$0.15
Cloudflare Workers AI `@cf/meta/llama-3.2-3b-instruct`	$0.051	$0.335
DeepInfra `deepinfra/meta-llama/Llama-3.2-3B-Instruct`	$0.02	$0.02
Fireworks AI `fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct`	$0.1	$0.1
Hyperbolic `hyperbolic/meta-llama/Llama-3.2-3B-Instruct`	$0.12	$0.3
IBM watsonx `watsonx/meta-llama/llama-3-2-3b-instruct`	$0.15	$0.15
Lambda `lambda_ai/llama3.2-3b-instruct`	$0.015	$0.025
Novita `novita/meta-llama/llama-3.2-3b-instruct`	$0.03	$0.05
OpenRouter `meta-llama/llama-3.2-3b-instruct`	$0.05	$0.33
SambaNova `sambanova/Meta-Llama-3.2-3B-Instruct`	$0.08	$0.16
Together AI `together_ai/meta-llama/Llama-3.2-3B-Instruct`	$0.06	$0.06

Cost Calculator

US Dollar ($)

Preset:

Input tokens

Output tokens

Number of calls

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 3.2 3B Instruct, ranked by cheapest on-demand price. The model needs about 7 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds

FP16 (full precision)

US Dollar ($)

Instance	Cloud	GPU	VRAM	Price
Standard_NV4as_v4	Azure	AMD Radeon Instinct MI25	16 GB	$0.233/hr
g5g.xlarge	AWS	T4g	16 GB	$0.420/hr
Standard_NV8as_v4	Azure	AMD Radeon Instinct MI25	16 GB	$0.466/hr
7 more instances can run Llama 3.2 3B Instruct Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

Version	Released	Context	Input / 1M	Output / 1M	Status
Llama 3.3 70B Instruct	2024-12-06	131K	$0.100	$0.200	Deprecated
Llama 3.2 3B Instruct	2024-09-25	131K	$0.015	$0.020	Current
Llama 3.2 1B Instruct	2024-09-25	131K	$0.020	$0.020	Deprecated
Llama 3.1 405B Instruct	2024-07-23	131K	$0.120	$0.300	Deprecated
Llama 3.1 8B Instruct	2024-07-23	200K	$0.020	$0.030	Deprecated
Llama 3.1 70B Instruct	2024-07-23	131K	$0.100	$0.100	Deprecated
Llama 3.1 70B	2024-07-23	128K	$0.360	$0.360	Available
Llama 3.1 8B	2024-07-23	131K	$0.030	$0.050	Available
Llama 3 70B Instruct	2024-04-23	131K	$0.120	$0.300	Deprecated
Llama 3 8B Instruct	2024-04-23	32K	$0.030	$0.040	Deprecated
Llama 3.1 Tulu3 405B	—	—	—	—	Available

Model IDs

@cf/meta/llama-3.2-3b-instruct

accounts/fireworks/models/llama-v3p2-3b-instruct

cloudflare/@cf/meta/llama-3.2-3b-instruct

deepinfra/meta-llama/Llama-3.2-3B-Instruct

eu.meta.llama3-2-3b-instruct-v1:0

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-instruct-3b

meta-llama-3-2-3b-instruct

meta-llama/llama-3.2-3b-instruct

meta-llama/llama-3.2-3b-instruct:free

meta-textgeneration-llama-3-2-3b-instruct

meta-textgenerationneuron-llama-3-2-3b-instruct

meta.llama3-2-3b-instruct-v1:0

meta.llama3-2-3b-instruct-v1:0:128k

novita/meta-llama/llama-3.2-3b-instruct

openrouter/meta-llama/llama-3.2-3b-instruct

sambanova/Meta-Llama-3.2-3B-Instruct

together_ai/meta-llama/Llama-3.2-3B-Instruct

together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo

us.meta.llama3-2-3b-instruct-v1:0

watsonx/meta-llama/llama-3-2-3b-instruct

Llama 3.2 3B Instruct

CapabilitiesAPIGET/api/v1/models/meta-llama-3-2-3b-instruct

Pricing by ProviderAPIGET/api/v1/models/meta-llama-3-2-3b-instruct/pricing

Cost CalculatorAPIGET/api/v1/models/meta-llama-3-2-3b-instruct/pricing/calculate?input_tokens=1000000&output_tokens=500000

Cheapest Instances to Run ItAPIGET/api/v1/models/meta-llama-3-2-3b-instruct/instances

VersionsAPIGET/api/v1/models?family=llama

Model IDsAPIGET/api/v1/models/meta-llama-3-2-3b-instruct

Capabilities

Pricing by Provider

Cost Calculator

Cheapest Instances to Run It

Versions

Model IDs