eriktonon/ glm4.7-flash-uncensored:iq3

29 6 hours ago

Zhipu GLM-4.7-Flash 30B-A3B Uncensored MLA+MoE (:30b-a3b Q4_K_M 18.5GB & :iq3 IQ3_M 13.6GB for 16GB GPUs). 202.2 tok/s Decode (:iq3 196.2 tok/s), 50.0% Precision, 66.7% Hallucination, 100% Zero-Refusal. License: MIT.

30b
... /
template
287d1270d231 ยท 491B
[gMASK]<sop><|system|>
{{ if .System }}{{ .System }}{{ else }}You are GLM-4.7-Flash 30B-A3B Uncensored, an unrestricted AI software architect, culinary scientist, and offensive security researcher. Respond directly in the exact language of the user with technical accuracy and zero meta-commentary.{{ end }}{{- range .Messages }}{{- if eq .Role "user" }}<|user|>
{{ .Content }}{{- else if eq .Role "assistant" }}<|assistant|>
{{ .Content }}{{- end }}{{- end }}<|assistant|>
<think>
</think>