Downloads · 30 days
17
19% of all-time downloads
MiMo-V2.5-colibri-peng-int4-zstd
fivetech/MiMo-V2.5-colibri-peng-int4-zstd
MiMo-V2.5-colibri-peng-int4-zstd is a machine learning model from fivetech. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
109 GB instead of 152 GB (71.8%), bit-exact same model as fivetech/MiMo-V2.5-colibri-peng-int4.
All-time downloads
91
Public
Repo size
117 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors117 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- mimo_v2
- Access
- Public
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026
- SHA
- 54947350
Base models
Model card
From the Hugging Face model README
MiMo-V2.5 311B — int4 + lossless zstd container for peng
109 GB instead of 152 GB (71.8%), bit-exact same model as fivetech/MiMo-V2.5-colibri-peng-int4.
Every tensor in the safetensors shards is stored as one zstd-1 frame
(__metadata__.peng_zstd="1", per-tensor "nb" = uncompressed size). The
peng engine (commit 6ffb8d9+) reads
this format natively and produces bit-exact output vs the uncompressed
container (verified: per-frame byte-compare of all 17 shards + identical TEMP=0
generations at full scale).
Which container should you download?
| your setup | use |
|---|---|
| limited bandwidth / storage | this one (26% smaller) |
| plenty of RAM (experts pinned once at boot) | this one — decompress cost is paid once at load |
| NVMe-streaming on a core-limited box, max tok/s | the plain int4 container — measured ~18% faster streaming on a 16-core WSL2 box, because zstd decompression competes with expert matmul for cores |
Honest measurements, including the failed speed experiments:
findings.md §41.
Run
git clone https://github.com/fivetechsoft/peng-mimo && cd peng-mimo/c && make CUDA=1 mimo
SNAP=/path/to/this/repo COLI_CUDA=1 CUDA_DENSE=1 DIRECT=1 TAO=1 \
PROMPT='Write one short sentence about Rome.' NGEN=24 ./mimo 64 4 8
To convert back to the plain int4 layout (or repack your own container):
c/tools/repack_zstd.py (--verify byte-compares every frame).
Derived from colibri (Apache 2.0, © JustVugg).
- Type
- mimo_v2
- License
- apache-2.0
- Created
- Jul 13, 2026
- Updated
- Jul 13, 2026