Llama 3.2 1B

Name: Llama 3.2 1B
Price: 0.071 USD
Author: Meta

Meta · Llama 3 · released 2024-09-25 · data checked 2026-11-01 Needs verification

Llama 3.2 1B is a 1.2B-parameter dense model from Meta (United States), released 2024-09-25 under the Llama 3.2 Community license. It doesn't have enough reported benchmarks for an index score yet. It needs about 1.5 GB of memory at 4-bit with an 8K-token context and costs $0.071 per million tokens through the cheapest API provider.

Small LM Index

—

Needs 2 core benchmarks (has 1)

Parameters

1.2B

Dense

Price per 1M tokens

$0.071

$0.027 in / $0.20 out · blended 3:1

Context window

128K

tokens

Benchmarks

Each bar shows this model's score. The tick marks the best tiny model on that benchmark. Sources: 1 reported by Meta. How we label sources.

GPQA Diamond Lab-reported Knowledge27.2

Class best: Nanbeige4.2 3B 87.4

Specifications

Lab: Meta (US · United States)
Architecture: Dense transformer
Total parameters: 1.2B
Active parameters: All (dense)
Size class: Tiny
Context window: 128K tokens
Input modalities: text
Reasoning: Instruct (no thinking)
License: Llama 3.2 Community
Openness: Open weights
Memory to run: ~1.5 GB at 4-bit, 8K context (more sizes)
Hugging Face: 1.8M downloads (30 days) · 1.9K likes
API providers: 1 on OpenRouter
API price: $0.027 in / $0.20 out per 1M (OpenRouter, 2026-11-03)

Weights on Hugging Face ↗Try on OpenRouter ↗

Compare with

Llama 3.2 1B vs LFM2.5 1.2B Thinking (1.2B, index 30.1)
Llama 3.2 1B vs LFM2.5 1.2B Instruct (1.2B, index 20.6)
Llama 3.2 1B vs EXAONE 4.0 1.2B (1.3B, index 36.1)

Sources

https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct

Something wrong here? Report it.

Run it locally

Uses unsloth/Llama-3.2-1B-Instruct-GGUF (Q4_K_M). Swap the tag for another size: BF16, F16, IQ4_NL, IQ4_XS, Q2_K, Q2_K_L, Q3_K_M, Q3_K_S….

Ollama

ollama run hf.co/unsloth/Llama-3.2-1B-Instruct-GGUF:Q4_K_M

llama.cpp

llama-server -hf unsloth/Llama-3.2-1B-Instruct-GGUF:Q4_K_M

Then open http://localhost:8080 for a chat window.

vLLM (GPU server)

vllm serve meta-llama/Llama-3.2-1B-Instruct

Full-precision weights, for a server GPU.

Open in LM Studio

Memory needed: weights, context cache and runtime buffers.

Quantization	4K context	32K context	128K context
16-bit F16	3.1 GB	4.0 GB	7.1 GB
8-bit Q8_0	1.9 GB	2.9 GB	6.0 GB
4-bit Q4_K_M	1.4 GB	2.3 GB	5.4 GB

Check it against your GPU, Mac or phone →