Llama 3.2 3B — pricing & specs
Llama 3.2 3B is a nano model from Meta, at capability tier 1 of 8. Live $/M-token pricing and specs from the Mintok catalog.
$/M-token pricing
Open-weights model — no per-token list price. Size your self-host $/M-token →
Specifications
- Vendor
- Meta
- Family
- Llama
- Capability tier
- 1 / 8
- Size class
- NANO
- Category
- GENERAL
- Parameters
- 3B total · 3B active (MoE)
- Context window
- 131,072 tokens
- Modality
- LLM
- Licensing
- Open-weights (OPEN_WEIGHTS)
Carbon footprint (modeled)
Modeled decode on a reference NVIDIA Rubin Ultra VR300 at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 1
Same capability tier, sorted by output price — the cheaper-capable options.
- Gemma 2 2BGoogleopen/M out
- Qwen2.5 3BAlibabaopen/M out
- Gemma 3 1BGoogleopen/M out
- Gemma 3 4BGoogleopen/M out
- Llama 3.2 1BMetaopen/M out
FAQ
How much does Llama 3.2 3B cost per token?
Llama 3.2 3B is distributed as open weights — there is no per-token list price; you self-host it. Use the Mintok sizing report to estimate your $/M-token at your volume.
What is Llama 3.2 3B's context window?
Llama 3.2 3B supports a 131,072-token context window.
What capability tier is Llama 3.2 3B?
Llama 3.2 3B sits at capability tier 1 of 8 on the Mintok scale (NANO size class).
Is Llama 3.2 3B open-source or proprietary?
Llama 3.2 3B is available as open weights under OPEN_WEIGHTS, so you can self-host it.
Put Llama 3.2 3B to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.