All models
Meta
Llama 3.2 3B Instruct fastruns locally
meta/llama-3-2-3b
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
Input / 1M
$0.051
USD per million tokens
Output / 1M
$0.34
USD per million tokens
Est. cost / token
$0.000000122
$0.12 per 1M, 3:1 mix
Context window
80K
max output 72K
Major features
Open weightsJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context2
- agentic1
Run it locally
Will it run on my machine? →ollama run llama3.2:3b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 2.7 GB |
| Q3_K_M | fair | 3 GB |
| Q4_K_Mrecommended | good | 3.4 GB |
| Q5_K_M | very good | 3.7 GB |
| Q6_K | excellent | 4.1 GB |
| Q8_0 | near-lossless | 4.9 GB |
| F16 | lossless | 8.1 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.051 | $0.34 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.051
- Output
- $0.34
- Blended (3:1)
- $0.12
Details
- Company
- Meta
- Version
- 3.2
- Family
- Llama
- Released
- 2024-09-25
- Parameters
- 3.2B
- Max output
- 72K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 46 min ago