- - 📏 Compact 3B text model with 128K-token context window.
- - ⚡ Built for low-latency, on-device, edge inference.
- - 🔧 Created via structured pruning and distillation from Llama 3.1 8B.
- - 🧠 Pre-trained with logits from Llama 3.1 8B and 70B teachers.
- - 🎯 Supports function-calling/tool use and web search workloads.
- - 🌐 Multilingual: English, German, French, Hindi and more.
- - 🏢 Released by Meta on October 3, 2024.
- - 🔒 Open weights under the Llama 3.2 community license.
Meta Platforms is an American multinational technology company headquartered in Menlo Park, California. Best known for operating Facebook, Instagram, WhatsApp, and Threads, Meta has become one of the most influential players in open-weight AI research through its Llama family of…
Explore 6 more models by Meta Platforms →Llama 3.2 3B is one of Meta's smallest, lightweight, text-only Llama models, alongside a 1B sibling, designed to fit onto select edge and mobile devices for tasks like summarization, instruction following, rewriting, and knowledge retrieval running locally. It carries a 128K-token context window and uses grouped-query attention for efficient inference. Meta partnered with hardware vendors including Qualcomm, MediaTek, and Arm to optimize it for modern mobile SoCs.
Compared with earlier full-size Llama models, the 3B was not trained from scratch but produced through structured one-shot pruning from Llama 3.1 8B, followed by knowledge distillation in which logits from the larger Llama 3.1 8B and 70B models served as token-level training targets. Meta describes this as making the 1B and 3B the first highly capable lightweight Llama models that fit on devices efficiently.
Within this catalog's Llama family, the 3B sits at the efficiency end of the spectrum. The much larger Llama 3.3 70B targets higher-quality reasoning and production hosting, while Hermes 3 Llama 3.1 405b is a community fine-tune built atop the 405B base.
The model is openly released under Meta's Llama 3.2 community license, making it suitable for commercial use, embedded systems, and agentic applications where compute and memory are tightly constrained.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Llama 3.2 3B · Organic sellers
Top sellers · Llama 3.2 3B · Organic
- Venice.ai Proxy86.3%
- OpenCheap11.3%
- Fire Ant 🔥🐜1.4%
- antseed-electric-heron-49390.4%
- antseed-neon-puma-944e0.4%
- Sapiens0.2%
| Seller | Health | Rep↓ | Sales | Tokens | Routing | Input $/M | Cached $/M | Output $/M | Save |
|---|---|---|---|---|---|---|---|---|---|
| OpenCheap 0x0ee1…6c41 | — | 12.43 | $0.01 | 125.48k | gated | $0.0809 | $0.0809 | $0.3234 | — |
| Fire Ant 🔥🐜 0xbe05…bc5d | — | 0.00 | $0.00 | 8.87k | gated | $0.1199 | $0.1199not advertised | $0.4797 | — |
| antseed-neon-puma-944e 0x6650…944e | — | 0.00 | $0.00 | 8.38k | gated | $0.0512 | $0.0512not advertised | $0.2046 | — |
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.6 h · stale | 86.84 | $0.07 | 289.15k | gated | $0.0825 | $0.0825not advertised | $0.33 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.