128K tokens
Context window
Llama 3.2 8B
Running on a laptop, classification, drafting
8K tokens
Max output
Local
Cost
late 2023
Knowledge cutoff
text
Modalities
Last verified 20 May 2026 Pricing is deliberately not listed here - check the vendor's own page. Report a correction
What it tends to refuse
Depends on the tuning
It takes about 5 GB at 4-bit and runs on a laptop with 16 GB of RAM. Give it one task per prompt and a simple output format.
Standing rules for this model go in Modelfile, not in every message.
See the config files.
Written for Llama
All 10- ConfigLlama
Modelfile for a consistent local persona
A Modelfile that fixes the system prompt and sampling parameters of a local model, so the same behaviour holds in every session and you stop retyping…
- Local setupLlama
Running your first local model
Ollama on an ordinary laptop, from install to a model answering in about ten minutes. It also shows how to work out which size fits before you…
Tested on Llama 3.2 8B · May 2026
Groq Cloud
Hosted inference on custom LPU hardware, built for speed. Open-weight models answer at a token rate that makes streaming feel close to instant.
Tested on Llama 3.3 70B · Jun 2026
Together AI
Hosted inference for open-weight models such as Llama, Mixtral and Qwen, plus fine-tuning, at a lower price than most proprietary-model APIs.
Tested on Llama 3.3 70B · Jun 2026
AnythingLLM
A desktop app for chatting with your own documents against a local or hosted model. The retrieval pipeline is built in, so you do not assemble it…
Tested on Llama 3.3 70B · Jun 2026
- CheatsheetLlama
Ollama commands worth knowing
The part of the CLI you will use, plus two flags that fix the problems everyone hits.
Tested on Llama 3.3 70B · May 2026