Kimi K2.7 Code

What Kimi K2.7 Code is for

Kimi K2.7 Code is trained for code. Moonshot AI released it in 2026-06 with no published dense parameter count, 128K of context and a Modified MIT 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 Kimi K2.7 code-specialized variant (June 2026), and it is the class of model an editor plugin such as Continue or Tabby points at.

Sizes and memory

Our catalogue does not carry a per-size memory breakdown for Kimi K2.7 Code, because no dense parameter count has been published for it. 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 Kimi K2.7 Code

Without a per-size memory figure there is no honest way to say which card holds Kimi K2.7 Code. 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 Kimi K2.7 Code: coding agents, multi-file refactoring, long-horizon code tasks. It is tagged code, MoE, agentic, coding-agents.

Where Kimi K2.7 Code sits in the Kimi family

Our catalogue holds 4 Kimi entries. Ordered by release date, Kimi K2.7 Code (2026-06) is the 4th of them, and the most recent. Kimi K2.5 and Kimi K2.6 carry the same recorded memory footprint, so choosing between those and this one is a question of behaviour rather than of hardware: Kimi K2.7 Code is the one recorded here for Kimi K2.7 code-specialized variant (June 2026).

It ships under the Modified MIT, which is neither a standard open-source licence nor a closed one. Read the terms before shipping anything commercial on top of 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 Kimi K2.7 Code 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 Kimi K2.7 Code 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 "Kimi K2.7 Code 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.