OSAIM
Open Source AI Models

Llama 3.2 3B

Long context (>100K)

Pocket-sized Llama 3 variant for edge deployment. Surprising chat quality after instruction tuning makes it competitive with much larger models from a previous generation. At Q4 it fits in ~2 GB of VRAM and runs on consumer GPUs and recent Apple Silicon. A strong default for on-device chat, summarisation, and structured extraction tasks where the workload doesn't need frontier reasoning quality.

Parameters
3B
Context length
128K
Modality
text
Released
2024-09-25

Memory & hardware

VRAM (fp16)
6 GB
VRAM (Q4)
1.8 GB
Recommended
RTX 3060 12GB / iPhone 15 Pro+
Quantizations
fp16, q8_0, q4_k_m, gguf

License: Llama 3 Community License

SPDX
Commercial use
Yes
Modification
Yes
Redistribution
Yes

Benchmarks

IFEval
77.4
unconfirmed
MMLU
63.4
unconfirmed
HumanEval
51.5
unconfirmed
MATH
48.0
unconfirmed
None of these scores has been confirmed against a source we can reach. How we verify.

Hosted inference pricing

No provider we track publishes a per-token price for this model today. What each one used to offer is listed below.

No longer listed

Providers that used to serve this model. We don't republish their old rates — the dates below are the provider's own.

  • groqGroq shut down llama-3.2-3b-preview on 14 April 2025.Source ↗

Run it yourself

Drop-in commands for the three most common open-source inference paths. The Ollama tag is a best-effort match against the registry; verify the size variant before pulling.

Run Llama 3.2 3B locally
Ollama (easiest)
ollama run llama3.2:3b
Single-line install + run; uses the official Ollama registry tag for this family.
vLLM (production)
vllm serve meta-llama/Llama-3.2-3B
High-throughput hosted inference; one command to expose an OpenAI-compatible HTTP server.
Transformers (Python)
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-3B")
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.2-3B", device_map="auto", torch_dtype="auto"
)
Direct PyTorch usage. Pin a torch / cuda version that matches your GPU.
Hugging Face ID: meta-llama/Llama-3.2-3B

Related models

Same family or similar size — useful when shopping around.

Llama 2 7B Chat
7B

The original 7B RLHF chat model. Historically important — the first widely-adopted commercially-usable open-weights chat model. Still cited as a baseline in most 2024–25 papers.

Context
4K
License
llama-2
VRAM Q4
4.2 GB
Llama 3.1 8B Instruct
8B

The workhorse 8B instruction-tuned model. Excellent quality-to-cost ratio and the broadest ecosystem support of any open-weights model — every major inference engine, fine-tuning library, and quantization toolchain has a 3.1 8B preset. Fits in 24 GB of VRAM at fp16, ~6 GB at Q4. Strong default for production chat where 70B is overkill, for fine-tuning on a specialist task, and for any workload where you want a known-good baseline.

Context
128K
License
llama-3
VRAM Q4
4.8 GB
Llama 3.2 11B Vision
11B

Llama 3's first vision-language model. Image understanding via a separately-trained ViT adapter bolted onto Llama 3 weights. Useful for OCR-adjacent workloads, document understanding, and image captioning at a permissive licence. The 11B size makes it cheap to host. Combined with the 128K text context, it handles long PDF-with-images workflows comfortably on a single 4090.

Context
128K
License
llama-3
VRAM Q4
6.6 GB
Phi-3 Mini 4K Instruct
3.8B

Microsoft's flagship small-model demonstration: GPT-3.5-class on academic benchmarks at <4B parameters. The 4K context-window variant is the lightest; a 128K variant ships separately. MIT licensed, well-suited to on-device assistants and structured-extraction workloads where compactness matters more than absolute quality.

Context
4K
License
mit
VRAM Q4
2.3 GB
Llama 3.2 1B
1B

The smallest Llama 3 release, designed for on-device inference on phones and laptops. The 1B model runs comfortably in <2 GB of RAM at Q4 quantization and is fast enough for real-time chat on a modern smartphone. Useful for edge inference, on-device assistants where round-tripping to a server is undesirable, and as a draft model for speculative decoding in front of a larger Llama 3 variant.

Context
128K
License
llama-3
VRAM Q4
0.6 GB
Falcon 3 7B Instruct
7B

TII's latest dense 7B from December 2024. Strong scores on commonsense reasoning benchmarks. TII's Falcon licence permits royalty-free commercial use with attribution.

Context
33K
License
falcon-2
VRAM Q4
4.2 GB