Marketplace · Text & chat

llama3.2:latest

Call llama3.2:latest through one OpenAI-compatible API. It's served by 2 hosts on the Inpherio grid, each at a price it sets — your request goes to the cheapest healthy one, and fails over to the next if it's down.

From
£0.054
per 1M output tokens
£1 buys about 19 million tokens (≈ 14 million words)
Hosts
2
Loaded now
0

At a glance.

tools

  • Type: Text & chat
  • Hosts serving it now: 2 (0 with it loaded in memory)
  • Engines: ollama
  • Context window: up to 131,072 tokens
  • Rentable: a whole host from £0.60 an hour (rentals)
python · openai sdk
from openai import OpenAI
client = OpenAI(base_url="https://inpherio.co.uk/v1",
                api_key=INPHERIO_API_KEY)
reply = client.chat.completions.create(
    model="llama3.2:latest",
    messages=[{"role": "user", "content": "Hello"}],
)

llama3.2:latest in detail.

Meta's Llama 3.2 goes small with 1B and 3B models.

Published by
meta-llama
Parameters
3.2B
Download size
2.0 GB (as packaged for Ollama)
Quantisation
Q4_K_M
Format
gguf
Architecture
llama
Licence
Llama 3.2 licence · access is gated (accept the terms on Hugging Face)
Task
text generation
Library
transformers
Languages
en, de, fr, it, pt, hi, es, th
First published
18 Sep 2024
Last updated
24 Oct 2024
Downloads (30 days)
886,379 on Hugging Face
Likes
2,963

llama text-generation facebook meta llama-3 en de fr it pt hi es th

The model card

Published by the model's authors on Ollama — shown as they wrote it, unedited by Inpherio.

The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.

Sizes

3B parameters (default)

The 3B model outperforms the Gemma 2 2.6B and Phi 3.5-mini models on tasks such as:

• Following instructions

• Summarization

• Prompt rewriting

• Tool use

ollama run llama3.2

1B parameters

The 1B model is competitive with other 1-3B parameter models. It’s use cases include:

• Personal information management

• Multilingual knowledge retrieval

• Rewriting tasks running locally on edge

ollama run llama3.2:1b

Benchmarks

Supported Languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages.

Sources: meta-llama/Llama-3.2-3B-Instruct on Hugging Face · llama3.2:latest on Ollama. Collected from public sources on 8 Nov 2026; the host serving it may run a different build or quantisation — the marketplace shows each host's own measurements.

Who's serving it.

Every host benchmarked this model on its own hardware before serving it. Prices are set by each host; health is scored by the platform from what it observes.

Hosts serving llama3.2:latest right now
HostTierPriceMeasured speedHealthStateRent
Lumaram-MacMini-M4-001L1£0.023 in · £0.054 out45 tok/s · 25 ms first token81loads on request—
GTX 1080 Ti (11G)L1£0.038 in · £0.086 out13 tok/s · 15219 ms first token78loads on request£0.60/h

Live data, refreshed on every visit. How billing works.

Room on the grid for your machine.

2 machines serve llama3.2:latest today. Every extra host is somewhere a request can fail over to when one drops, and spare capacity when demand spikes. The router weighs price, measured speed, health and whether the model is already loaded — so a host with a sharper price or quicker hardware wins the next call.

Hosts now
2
0 loaded in memory
Price to beat
£0.054
per 1M output tokens
Fastest measured
45 tok/s

Set your own price — you keep 85% of what it earns, and new hosts start with 12 months fee-free (up to £250 of earnings). A payout fee of £2 + 1% per payout to a UK bank account, £2 + 2% to any other country applies when you're paid. Install the connector, load llama3.2:latest, and the platform benchmarks it on your hardware before your first request.