Short answer: yes, Colibrì has demonstrated GLM-5.2 on a machine with 25GB of RAM by keeping the dense core resident and streaming routed experts from NVMe. But the model still occupies about 372GB on disk, and the project reports only 0.05 to 0.1 tokens per second on its 25GB baseline. This is a research breakthrough, not a fast laptop deployment.
What Colibri is, and what it is not
Colibrì is an Apache 2.0 inference engine and research platform written primarily in C. It is not a model, a new quantization of GLM-5.2, or a smaller distilled checkpoint. Its central idea is to treat VRAM, system RAM and fast storage as one managed hierarchy instead of requiring every parameter to remain in expensive memory.
The engine currently supports four distinct MoE families through sibling runtime implementations: GLM-5.2, Thinking Machines' Inkling, Moonshot AI's Kimi K3 and AI2's OLMoE. The same command-line, server and web interfaces sit above them.
How can a 744B model use only 9.9GB of resident RAM?
The answer is sparsity. GLM-5.2 contains 744B total parameters, but only about 40B are active for each token. Colibrì separates the weights that must remain available on every pass from the routed experts that change token by token.
VRAM
Hot experts and GPU work when available
System RAM
Dense attention, shared experts and a learned cache
NVMe storage
About 370GB of GLM-5.2 routed experts, loaded on demand
The much-shared 9.9GB resident number describes the dense part of the int4 GLM-5.2 container. It does not mean GLM-5.2 has become a 9.9GB model. The routed expert bank still exists, still needs hundreds of gigabytes of storage and still has to cross the storage bus when the router selects an expert that is not cached.
The measured speed tells the real story
Colibrì's documentation is unusually clear that there is no speed SLA. The following figures are project-reported measurements on different community and development systems, not LocalClaw benchmark reproductions. They show how the same model moves from proof-of-possibility to something closer to interactive use as more weights become resident.
| Hardware shape | Reported decode | What it means |
|---|---|---|
| 25GB development box | 0.05-0.1 tok/s | Ten to twenty seconds per token. A correctness and accessibility proof. |
| Single RTX 5070 Ti laptop-class system | 1.07 tok/s | Usable for patient experimentation, still slow for daily chat. |
| 128GB CPU-only desktop | ~1.8 tok/s warm | A more credible private research workstation path. |
| 6 x RTX 5090, full expert residency | 5.8-6.8 tok/s | Interactive, but no longer ordinary consumer hardware. |
Storage speed, cache state, prompt routing, backend and expert residency all change performance. A second independent NVMe can help because Colibrì can distribute expert reads across drives, but the project itself asks users to measure rather than assume a universal gain.
Which models does Colibri run?
| Family | Scale | Storage / resident reality | Practical verdict |
|---|---|---|---|
| GLM-5.2 | 744B / 40B active | 372GB int4 container; 9.9GB dense resident core | Best documented Colibrì path |
| Inkling | 975B / 41B active | About 469GB; optional 15.3GB quantized dense set | Runnable on 25GB, very slow from NVMe |
| Kimi K3 | 2.8T / 104B active | About 1.45TB of routed experts; ~35GB dense set at 4-bit | Text-only research path, not a daily driver |
| OLMoE | 7B / 1B active | Converted local container | Small validation and experimentation target |
Engine support does not change each model's license. Colibrì itself is Apache 2.0, while Kimi K3 remains governed by Moonshot's custom model license and other weights retain their own terms.
Does this make Kimi K3 a consumer local model?
No. It makes a previously unthinkable text-only research run technically possible. Colibrì's Kimi K3 implementation streams the checkpoint's native MXFP4 experts directly and quantizes the dense set at load time. The project documents approximately 1.45TB of expert data and a resident dense set of about 35GB at 4-bit.
In a measured 93-layer run, the project reports that direct I/O reduced output time from roughly 21 seconds per token to about 9.4 seconds per token. That is meaningful systems progress, but it remains far from an interactive assistant. The Colibrì path is also text-only and does not load Kimi K3's vision tower.
Installation and platform support
Colibrì publishes prebuilt archives for Linux, macOS and Windows, while the engine can also be built from source with GCC or Clang plus OpenMP. The engine is pure C, but the launcher, conversion helpers and API gateway use Python 3. The model download is the real installation cost: GLM-5.2 alone needs about 372GB plus safe free-space headroom.
Use v1.4.0 or newer for the new model families
The August 1 release notes say earlier v1.3 archives omitted the extra model binaries, so Kimi K3 and Inkling could not work from those packaged downloads. Version 1.4.0 corrects that packaging issue. This is a fast-moving project: pin the exact release, container and command when reporting a result.
Why this matters for LocalClaw and OpenClaw
Colibrì exposes an OpenAI-compatible API with /v1/chat/completions, plus an Anthropic-compatible /v1/messages endpoint. That makes it conceptually relevant to local control centers and agent tools: a compatible client can point at the local server instead of a hosted provider.
But compatibility is not the same as product readiness. LocalClaw should treat Colibrì as an experimental advanced runtime, not silently install it or recommend GLM-5.2 to ordinary Macs. A future integration would need reproducible macOS tests, disk-space checks, a clear speed warning, version pinning and a recovery path before it belongs in a one-click setup.
You are doing inference research
You have hundreds of gigabytes of fast storage, accept experimental setup work and want to study enormous MoE models locally.
You want a fast daily assistant
A smaller GGUF or MLX model that fits in RAM will be dramatically simpler, faster and easier to maintain.
LocalClaw verdict
Colibrì is one of the most interesting local inference projects of 2026 because it attacks the memory wall instead of merely publishing another quant. It proves that a model can remain semantically intact while its weights are staged across storage, RAM and VRAM according to measured routing behavior.
The honest conclusion is equally important: runnable does not mean comfortable. On 25GB, GLM-5.2 is a slow experiment. At 128GB it becomes more credible. With six RTX 5090 cards and full residency it becomes interactive. Colibrì expands what is possible on hardware you own, but it does not repeal bandwidth, capacity or latency.
Frequently asked questions
Is Colibri an open-source model?
No. Colibri is an Apache 2.0 inference engine and research platform. It runs supported model families whose weights retain their own licenses.
Can GLM-5.2 really run with 25GB of RAM?
Yes, the project reports a proven 25GB baseline by streaming experts from a roughly 372GB NVMe container. Performance at that floor is only 0.05 to 0.1 tokens per second.
Does 9.9GB resident mean GLM-5.2 is a 9.9GB model?
No. That figure covers the dense resident part of the int4 runtime. Roughly 370GB of routed experts remain on storage and are loaded or cached as needed.
Can Colibri run Kimi K3 on a normal PC?
It can technically stream the text model from about 1.45TB of expert data, but the documented output remains measured in seconds per token. This is a research path, not normal interactive use.
Is Colibri compatible with OpenAI clients?
Yes. Its server implements OpenAI-compatible model and completion endpoints and also exposes an Anthropic Messages API endpoint. Client compatibility does not guarantee practical speed on minimum hardware.
Sources
- Colibrì official repository and README: architecture, measurements, supported models and setup
- Colibrì v1.4.0 release notes and packaging correction
- Official OpenAI and Anthropic-compatible API documentation
- Official Kimi K3 runtime notes, storage layout and measured I/O results
- Official Inkling runtime notes and low-memory dense conversion
- Recommended GLM-5.2 Colibrì int4 container