Hermes 3

What Hermes 3 is for

Hermes 3 is a general-purpose open-weights model from Nous Research, released in 2024-08 with 4 sizes (3B, 8B, 70B, 405B) and 128K of context, licensed Apache 2.0. The catalogue records its strength as uncensored chat with strong function calling.

Sizes and memory

The 3B needs about 2 GB of weights at Q4_K_M and the 405B about 240 GB, a spread of 238 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
3B	2 GB	3 GB	NVIDIA Jetson Orin Nano 8GB
8B	6 GB	9 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 Hermes 3

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Hermes 3 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 3 recorded uses for Hermes 3: function calling, uncensored chat, agentic. It is tagged chat, tools, function-calling, uncensored.

Where Hermes 3 sits in the Hermes family

Hermes 3 is the only Hermes entry in our catalogue, so there is no in-family alternative to weigh it against; the comparison to make is against the models listed at the foot of this page.

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 Hermes 3 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 Hermes 3 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 "Hermes 3 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.