GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CosmicRaisins
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
CosmicRaisins
Model Tree
CosmicRaisins/GLM-5.2-AWQ-INT4-15pct
Input Modalities
Output Modalities
Supported Functionality
markdown
--speculative-config '{"model":"CosmicRaisins/GLM-5.2-MTP-INT4-aligned","method":"mtp","num_speculative_tokens":3,"attention_backend":"FLASHMLA_SPARSE"}'
k=3 benched best for me on a synthetic corpus; Z.ai recommends k=5, and I haven't compared them in real-world use yet. Serving stack: github.com/CosmicRaisins/glm-5.2-gb10.
The MTP weights trace to GLM-5.2's native MTP head (Z.ai, MIT), sourced via
0xSero's NVFP4 layer-78 (0xSero/GLM-5.2-NVFP4-REAP-469B), then dequantized,
re-quantized to INT4, expert-pruned to 218, and aligned to the DeepSeekMTP
loader layout. The reconstruction and alignment are mine.
License MIT, inherited from the GLM-5.2 base: the MTP weights carry GLM-5.2's MIT grant through 0xSero's quantization (0xSero's repo declares no explicit license). Attributed to Z.ai and 0xSero; not affiliated with either.