meta-llama

Meta: Llama 3.2 3B Instruct

The Meta Llama 3.2 3B Instruct model is a text-based AI that handles input and output in the form of text. It operates within a context length of 131,072 tokens and can produce up to 117,964 completion tokens per interaction. For those looking for a balance between cost and performance, Meta Llama 3.2 3B Instruct might be worth considering, particularly given its price point of $0.05/M input token and $0.33/M output token. Its blended benchmark score of 3.9, achieved across one independent benchmark, indicates some level of capability in this area; however, it does not support tools or reasoning tasks.

Open weights 3.21B parameters, about 1.8 GiB at Q4_K_M: fits comfortably on 18 of 18 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
76/100
price + capability + benchmarks
Input Price
$0.05
per 1M tokens · checked 2026-09-23
Output Price
$0.33
per 1M tokens · checked 2026-09-23
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 3.6 across 1 benchmark, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 9.4
Model ID
meta-llama/llama-3.2-3b-instruct
Vendor
meta-llama
Released
September 2024
Tokenizer
Llama3
Input Modalities
text
Output Modalities
text
Max Output
117,964 tokens
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.05/M input and $0.33/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.04
A month of a busy support chatbot 5M in / 2M out $0.91

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-23 $0.05 $0.33 131,072
2026-07-17 $0.05 $0.34 131,072

Similar models

Quick answers

How much does Meta: Llama 3.2 3B Instruct cost?
$0.05 per million input tokens and $0.33 per million output tokens.
What is Meta: Llama 3.2 3B Instruct's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Meta: Llama 3.2 3B Instruct support tool calling?
It supports structured output.
Can Meta: Llama 3.2 3B Instruct process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.