Mistral Nemo

What Mistral Nemo is for

Mistral Nemo is a general-purpose open-weights model from Mistral AI + NVIDIA, released in 2024-07 with a single 12B size and 128K of context, licensed Apache 2.0. The catalogue records its strength as 12B class chat with 128K context.

Sizes and memory

The 12B needs about 8 GB of weights at Q4_K_M. That is the whole range; there is no larger or smaller variant in this record. 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
12B	8 GB	12 GB	NVIDIA RTX 3060 12GB

Hardware that runs Mistral Nemo

18 of the 19 cards in our hardware guide hold at least one size of Mistral Nemo at Q4_K_M. The cheapest that does is the NVIDIA RTX 3060 12GB at about $250, running the 12B.

The largest size any of them holds is the 12B at 8 GB, on the NVIDIA RTX 3060 12GB (12 GB at 360 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 4 recorded uses for Mistral Nemo: chat, RAG, long-context, tools. It is tagged chat, instruction, tools, multilingual.

Where Mistral Nemo sits in the Mistral family

Our catalogue holds 4 Mistral entries. Ordered by release date, Mistral Nemo (2024-07) is the 2nd of them, and Mistral Small (2025-03) is newer.

The Apache 2.0 licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.

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 Mistral Nemo 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 Mistral Nemo 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 "Mistral Nemo 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.