Llama 3.2 3B
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
Hosted inference pricing
USD per million tokens.
| Provider | Input | Output | |
|---|---|---|---|
| groqCheapest | $0.06 | $0.06 |
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.
ollama run llama3.2:3b
vllm serve meta-llama/Llama-3.2-3B
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"
)meta-llama/Llama-3.2-3B Related models
Same family or similar size — useful when shopping around.
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'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
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
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
The original Mistral 7B refresh with 32K context and extended vocabulary. Permissive Apache 2.0 weights and the first widely-deployed sliding-window-attention model. Still useful in 2026 for very-low-cost inference and as a baseline for fine-tuning experiments.
- Context
- 33K
- License
- apache-2-0
- VRAM Q4
- 4.2 GB
Apache-2.0-licensed 7B model with surprisingly strong reasoning and multilingual chops. Qwen 2.5 trains on a larger and more carefully filtered corpus than the original Qwen series, and the 7B variant punches well above its weight on coding and math benchmarks. A strong default for cost-sensitive chat workloads and for fine-tuning experiments where the Apache licence simplifies downstream redistribution.
- Context
- 128K
- License
- apache-2-0
- VRAM Q4
- 4.2 GB