GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
WaveCut
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
WaveCut
Model Tree
deepseek-ai/DeepSeek-V4-Flash-0731
Input Modalities
Output Modalities
Supported Functionality
≈96 GB of sharded Safetensors plus config and tokenizer. Everything follows the
original 0731 format, so tooling that understands the base model understands this one.
The config and tokenizer load fine with AutoConfig / AutoTokenizer; per-layer
pruning choices are recorded in SELECTION.json.
The model's built-in speculative decoder (three extra MoE stages that draft tokens
ahead) is preserved untouched under its mtp.* tensor namespace. In the GGUF release
it ships as a separate optional file — see the companion repo.
One pruning step, straight from the original — no cascading. Expert importance was
measured by running deepseek-ai/DeepSeek-V4-Flash-0731
over a ~5-million-token calibration mix (multi-turn dialogs, thinking and direct modes,
rendered with the model's own chat encoder). The strongest experts of every domain were
protected from pruning, the survivors were carried over byte-identical, and the
router was re-balanced to keep the original selection behavior.
| Calibration domain | Share |
|---|---|
| Code | 35% |
| Agentic / tool use | 19% |
| Multilingual chat | 16% |
| Math | 8% |
| General chat | 6% |
| Roleplay | 6% |
| Russian | 5% |
| Long docs | 4% |
This line replaces the earlier cascaded REAM builds (now archived under -exp names),
which degraded badly in multi-turn use.
Every scenario is a live multi-turn conversation, run on the companion 2-bit GGUF build — the only runnable form of this checkpoint. Treat the results as a lower bound for this full-precision source (raw evidence ships in the companion repo's SMOKE_REPORT.json).
| Scenario | Result |
|---|---|
| Russian wordplay, multi-turn | ✅ |
| English → Russian code-switching | ✅ |
| Code Q&A over a 4k-token file | ✅ |
| Tool calling (DSML) | ❌ |
| Russian multi-turn reasoning | ✅ |
| Spanish creative writing | ✅ |
| Code refactoring | ❌ |
| Chinese summarization | ✅ |
| Long-dialog focus (drift check) |
| ✅ |
| Tool call → code chain | ❌ |