GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
wrldsuksgo2mars
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
wrldsuksgo2mars
Model Tree
zai-org/GLM-5.3-Flash-BF16
Input Modalities
Output Modalities
Supported Functionality
gate_proj, up_proj, and
down_proj tensors in target layers 3…44 plus checkpoint MTP layer 45.f12e0fe1f6b2ea274c11a569582edfd99d993c5e.Quantization used GPTQModel 0565af7ce20a93df9bbc0e5563d7c6f60916f41a, EXL3 MCG K3, seed 787,
sigma_reg=0.025, automatic output-scale selection, and a fixed 1,426-record
calibration corpus (sha256:4e569625d97865777da92167b8fbf6fabb4ab7adf55baa5d676c81ce8dd95244). Natural GLM router
traffic supplied expert Hessians; the committed recovery contract covers any
expert below the 1,024-route floor. The full error ledger and validation report
ship with the model.
Before upload, the fully materialized checkpoint is loaded directly by the
two-GPU B12x/vLLM recipe with adaptive MTP5 and NVFP4 MLA. Publication is gated
on ordinary generation plus five strict tool-call scenarios. The exact prompts,
expected behavior, actual calls, and raw report ship in
quantization/vllm-prompt-expected-actual.md and
quantization/vllm-tool-eval.json.
This is intended for the optimized two-GPU GLM-5.3 recipe at
tpurtell/glm-5.3-flash-ext3-4-bit-2x-rtx.
That runtime carries the GLM/EXL3/MTP and B12x ports; this card does not claim
stock-vLLM support.
Huge thanks to Z.ai for GLM-5.3 Flash, Brandon for the earlier K4 quant and qualification work that helped inform this run, MiaAI-Lab for the nearby dual-DGX-Spark reference, and the GPTQModel, ExLlamaV3, vLLM, and B12x contributors.
sha256:e6007bd58fb7e07f9fe69544257ee2713f252ef5855bbf685b48c991d524ef0fsha256:fdce3c2c0078e27b0fa8bdab92cbd13f6c0ab34fb8d3e836fc56b44afc4ec82csha256:625dcdfc8a031506d1406804cc72b7373c600567e076220b756f9504bc0fd284