This commit is contained in:
Dobromir Popov
2026-07-21 14:00:30 +03:00
parent cd6b4d9d48
commit 505f37dd8d
21 changed files with 2653 additions and 0 deletions

View File

@@ -95,6 +95,16 @@ CURATED_MODELS: list[ModelPreset] = [
vram_bf16=3.2,
description="Fast no-gating model — good quality, ~3 GB",
),
ModelPreset(
name="Qwen2.5-Coder-1.5B-Instruct-Q2_K-GGUF",
hf_repo="alal123/Qwen2.5-Coder-1.5B-Instruct-Q2_K-GGUF",
num_layers=28,
vram_nf4=0.7,
vram_int8=1.0,
vram_bf16=3.2,
description="GGUF-quantized Qwen2.5 Coder 1.5B Instruct (Q2_K, ~676 MB)",
aliases=("qwen2.5-coder-1.5b-instruct-q2_k-gguf",),
),
ModelPreset(
name="Llama-3-70B-Instruct",
hf_repo="meta-llama/Meta-Llama-3-70B-Instruct",