GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
staccs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
staccs
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
The assimilation kit refuses to call a model anything but an UNVERIFIED claim until perplexity is measured before vs after. Our run (RTX 3060, 2026-08-16, fp16):
| metric | original | assimilated | delta |
|---|---|---|---|
| perplexity, kit's eval sample | 2.506 | 2.528 | +0.86% |
| perplexity, full wikitext-2 test (sliding window, 2048/1024) | 15.2443 | 15.2389 | −0.04% |
The kit's own standard, quoted: "RETENTION MEASURED: within 2% on this sample. Run a full corpus (wikitext) before shipping." Done: on the full wikitext-2 test set the assimilated model is marginally better than the original. Same pass, independently reproduced on an RTX 4090 with digit-identical sample deltas (+0.86% on both boxes) — the pipeline is deterministic end to end.
model.safetensors-* — the dense assimilated weights (full original shape,
because transformers/llama.cpp demand the original architecture).*.unicron_report.json — the receipt: per-shard, per-layer rank reports of
what the Marchenko–Pastur filter kept vs dropped.*.lecore.safetensors — the factored form: each filtered layer as its
thin (U, V) pair. This is the model's true information size (~2× smaller on
the rehearsal subject). Loads via leCore's unicron_reconstruct; a
transformers shim that runs the factored form directly is upstream's planned
next step.Marchenko–Pastur filtering treats each weight matrix's singular value spectrum as signal + noise: the MP distribution predicts exactly what the spectrum of a random matrix of that shape looks like, so singular values above the MP edge are learned structure and the bulk below it is indistinguishable from initialization noise. Unicron keeps the outliers, drops the bulk, and rebuilds. Embeddings and norms are policy-skipped; layers whose outliers carry <1% of energy are guarded rather than filtered (random ≠ useless — measured, not assumed). The engine that rewrites the weights is NumPy + stdlib only; torch lives only in the measurement harness.
Three commands, no HF account needed (the kit downloads anonymously):
bash
git clone https://github.com/AnOversizedMooseWithSocks/leCore.gitcd leCore./assimilation/assimilate.sh --eval # download + assimilate + measure./assimilation/chat.sh --both # same prompt to both models, side by side
A private venv appears at assimilation/.venv; your system Python is never
touched.
assimilate.sh --eval, stock settings.