Avg. Total Time
31.11s
Avg. TTFT
4.70s
Avg. Prefill TPS
2541.75
Avg. Gen TPS
19.86
Context Size
131072
Quantization
r32
Engine
aphrodite
Creation Method
LoRA Finetune
Model Type
GLM45A
Chat Template
GLM4
Reasoning
Yes
Vision
No
Parameters
106B
Added At
10/3/2025
base_model:
Drummer proudly presents...

The smoke and the fire and the speed, the action and the sound, and everything that goes together, the steam engine is the most beautiful machine that we ever made, there's just nothing like it.
Steam v1 has got the juice
Characters are as vivid as the original GLM-Air, though prose is much more enticing.
Damn okay this model is actually pretty good. I don't have enough vram to test it on longer chats to 16k, but on 6k chats it's looking good and without deepseek's slop.
this model has a unique way of speaking. imo it's kept the same "soul" of the writing as Air but with more creativity and willingness to be hor -
this model is fun! :3

Thank you to Nectar.AI for making this finetune possible, and your belief and support for Generative AI as entertainment!
Thank you, zerofata, for collaborating with me and diving headfirst on tuning GLM Air!
config-v1b