PsyGuard-Qwopus-27B-alpha

Experimental coding model. Fine-tune of Jackrong/Qwopus3.6-27B-Coder.

alpha โ€” experimental. Internal evals only. Dogfood at your own risk.

Format: Q5_K_M GGUF (llama.cpp / LM Studio / Ollama).

The GGUF bundles an MTP draft head โ€” runs as a normal model, or ~1.8ร— faster with speculative decode in llama.cpp: --spec-type draft-mtp --spec-draft-n-max 2

Downloads last month
31
GGUF
Model size
27B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

5-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for thetom-ai/PsyGuard-Qwopus-27B-alpha

Quantized
(27)
this model