GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
OO-LD
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OO-LD
Model Tree
unsloth/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
| base | unsloth/Qwen3.5-4B |
| rank | 16 |
target_modules | all-linear |
| steps | 1000 |
| examples | 1,000 |
| corpus | generated quantity documents, 100 classes, QUDT units |
| evaluated on | Wiki-Measurements, held-out class half, human prose |
Trained on machine prose and scored on human prose, deliberately: the register is held out so a score is not a report on the generator.
vLLM, loaded beside the base so the pair differs in the adapter and nothing else:
text
vllm serve unsloth/Qwen3.5-4B --enable-lora --lora-modules oold=OO-LD/oold-lean-qwen4b-r16-s1000 --max-lora-rank 16--max-lora-rank has to be at least the rank, or the adapter loads and
changes nothing. An adapter loaded at runtime through
POST /v1/load_lora_adapter does not survive scale-to-zero.
The catalogue is worth more than the tune. Untuned with the class list in the prompt the same base reaches 0.873 on this task, above every adapter here, so this is a way to buy a short prompt and not a way to buy accuracy.
Across 4B to 32B in two families, parameter count orders neither the base score nor the gain. The numbers and the method are on the benchmark.