mirror/QodeAssist
1
0
Fork 0
mirror of https://github.com/Palm1r/QodeAssist.git synced 2026-07-07 13:39:11 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add more agents

Browse Source
This commit is contained in:
Petr Mironychev
2026-07-03 09:49:42 +02:00
parent 35bbaa1af0
commit bf3a67a1eb
9 changed files with 102 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
sources/agents/lmstudio_compression_gemma4_26b_a4b.toml Normal file
View File

@@ -0,0 +1,11 @@
schema_version = 1
extends = "LM Studio Compression"
name = "LM Studio Compression — 24 GB (Gemma 4 26B A4B)"
description = "Balanced tier. Conversation summarization on Gemma 4 26B-A4B QAT (Q4_0) — ~18 GB resident, 24 GB. Mixture-of-experts (~4B active) so it summarizes at ~12B speed with more capacity. Reasoning disabled via reasoning.effort=none for a direct summary. Point the LM Studio (Responses API) provider URL at your host."
model = "google/gemma-4-26b-a4b-qat"
tags = ["compression", "lmstudio", "responses", "local", "gemma4", "24gb"]
[body]
reasoning = { effort = "none" }