mirror of
https://github.com/Palm1r/QodeAssist.git
synced 2026-07-06 04:59:14 -04:00
15 lines
785 B
TOML
15 lines
785 B
TOML
schema_version = 1
|
|
|
|
extends = "LM Studio Chat"
|
|
name = "LM Studio Chat — 16 GB (Gemma 4 12B)"
|
|
description = "Light tier. Local LM Studio coding chat on Gemma 4 12B QAT (Q4_0) — ~7 GB weights, ~10 GB resident at 8K context; comfortable on 16 GB (runs on 12 GB). Fastest to load, best for quick iterations. Native reasoning + tools + vision. Point the LM Studio (Responses API) provider URL at your host. Note: on LM Studio the context length (KV cache) is a model-load setting, not per-request — the agent's only memory lever is the model."
|
|
|
|
model = "google/gemma-4-12b-qat"
|
|
enable_thinking = true
|
|
tags = ["chat", "lmstudio", "responses", "local", "gemma4", "16gb"]
|
|
|
|
[body]
|
|
temperature = 1.0
|
|
top_p = 0.95
|
|
max_output_tokens = 16384
|