Llama 3.1
Meta's flagship open-weights LLM. Strong all-rounder with native tool use, 128K context, and broad ecosystem support.
What Llama 3.1 is for
Llama 3.1 is trained for code. Meta released it in 2024-07 with 3 sizes (8B, 70B, 405B), 128K of context and a Llama 3.1 Community License licence. Context length matters more here than for chat, because a coding assistant that cannot see the whole file is guessing. The catalogue records its strength as general-purpose chat, agentic workflows, code, and it is the class of model an editor plugin such as Continue or Tabby points at.
Sizes and memory
The 8B needs about 5 GB of weights at Q4_K_M and the 405B about 240 GB, a spread of 235 GB across the family. The catalogue's default pick is 8B. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.
| Size | Weights at Q4_K_M | Recommended VRAM | Smallest card in our guide that holds it |
|---|---|---|---|
| 8B | 5 GB | 8 GB | NVIDIA Jetson Orin Nano 8GB |
| 70B | 42 GB | 63 GB | Apple M3 Ultra |
| 405B | 240 GB | 360 GB | None in this guide |
Hardware that runs Llama 3.1
Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Llama 3.1 at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 8B.
The largest size any of them holds is the 70B at 42 GB, on the Apple M3 Ultra (192 GB at 800 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.
What people use it for
The catalogue lists 5 recorded uses for Llama 3.1: chat, code, RAG, agentic, summarization. It is tagged chat, instruction, tools, agentic, code.
Where Llama 3.1 sits in the Llama family
Our catalogue holds 7 Llama entries. Ordered by release date, Llama 3.1 (2024-07) is the 3rd of them, and Llama 4 (2025-04) is newer.
The Llama 3.1 Community License is a vendor community licence rather than a standard open-source one: usable, redistributable with attribution, and carrying conditions that are worth reading before you build a product on it.
Context window: 128K
128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.
How to run Llama 3.1 locally
Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.
Option 1: Ollama (simplest)
# find the tag for Llama 3.1 at ollama.com/library
ollama run <tag>Option 2: Mullama (production)
mullama pull <tag>
mullama run <tag>Option 3: llama.cpp (CLI)
# download a GGUF from Hugging Face, searching for "Llama 3.1 GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"Option 4: Python with Mullama or llama-cpp-python
from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))Sources
Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.