You can deploy this model and start earning money today!

callgg/
qwen3.8-27b-gguf

Name: qwen3.8-27b-gguf
Availability: InStock

Views

No views yet

qwen3.8-27b-gguf

execute tools and/or agentic workflow
fit in 12GB vram/ram or less

run it with ggk

ggk server engine -- -m qwen3.8-27b-q2_k_s.gguf --mmproj mmproj-qwen3.8-27b-q4_0.gguf --jinja --spec-type draft-mtp -md mtp-qwen3.8-27b-q4_0.gguf --spec-draft-n-max 2 --parallel 1 -ts 1,0

or run it with llama.cpp

./llama-server -m qwen3.8-27b-q2_k_s.gguf --mmproj mmproj-qwen3.8-27b-q4_0.gguf --jinja --spec-type draft-mtp -md mtp-qwen3.8-27b-q4_0.gguf --spec-draft-n-max 2 --parallel 1 --host 127.0.0.1 --port 8888

or opt lmstudio, etc.

callgg/qwen3.8-27b-gguf

qwen3.8-27b-gguf

callgg/
qwen3.8-27b-gguf