GLM-5

What GLM-5 is for

GLM-5 is a reasoning model: it spends output tokens working through a problem before answering, which makes it slower per useful word and better on problems that need the working shown. Z.ai released it in 2026-02 with a single 744B (40B active MoE) size under MIT, with a 128K context window. Budget for the extra tokens the thinking phase consumes. The catalogue records its strength as frontier-tier reasoning and agentic engineering.

Sizes and memory

Our catalogue does not carry a per-size memory breakdown for GLM-5. What it records instead is a floor of 256 GB and a recommended 512 GB for the default configuration. Until a per-size figure exists, treat those two numbers as the whole guidance rather than reading a size table that would have to be invented.

Hardware that runs GLM-5

Without a per-size memory figure there is no honest way to say which card holds GLM-5. Its recorded floor of 256 GB rules out every consumer card in our hardware guide, which tops out well below that.

What people use it for

The catalogue lists 3 recorded uses for GLM-5: frontier reasoning, agentic coding, long-horizon tasks. It is tagged reasoning, thinking, agentic, MoE, frontier.

Where GLM-5 sits in the GLM family

Our catalogue holds 5 GLM entries. Ordered by release date, GLM-5 (2026-02) is the 2nd of them, and GLM-5.2 (2026-06) is newer. GLM-5.1 and GLM-5.2 carry the same recorded memory footprint, so choosing between those and this one is a question of behaviour rather than of hardware: GLM-5 is the one recorded here for frontier-tier reasoning and agentic engineering.

The MIT 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.

Read the GLM-5.2 page instead

Our catalogue records the same publisher, the same size, the same 256 GB memory floor and the same 128K context window for GLM-5, GLM-5.1, GLM-5.2. Where we cannot show you how two releases differ in anything a reader would act on, publishing both as competing search results would be a guess dressed as a recommendation.

So GLM-5.2 (2026-06), the most recent of the 3, is the one we put in front of that question, and this page is marked noindex. It stays published because the record is real and someone running GLM-5 today should still be able to look it up. When a figure appears that separates them, this page returns to the index on its own.

How to run GLM-5 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 GLM-5 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 "GLM-5 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.