ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

studio: sort GGUF dropdown client-side -- recommended first, OOM last, rest by size descending

Browse source 
Move the sort logic from the backend to the frontend GgufVariantExpander
component where GPU VRAM info is available. The backend now does a simple
size-descending sort. The frontend pins the recommended variant at the
top, pushes OOM variants to the bottom, and sorts the rest by file size
descending (largest/best quality first).
This commit is contained in:
Daniel Han 2026-03-15 05:54:27 +00:00
commit 3c1b8d7ab7
2 changed files with 23 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

16
studio/backend/utils/models/model_config.py
View file

@ -962,18 +962,10 @@ def list_gguf_variants(
)
)
# Sort: recommended first, then UD variants by size, then non-UD by size.
best_file = _pick_best_gguf([v.filename for v in variants])
best_quant = _extract_quant_label(best_file) if best_file else None
def _sort_key(v: GgufVariantInfo) -> tuple:
is_recommended = v.quant == best_quant
is_ud = v.quant.startswith("UD-")
# (0, ...) recommended | (1, 0, -size) other UD | (1, 1, -size) non-UD
# Negative size so largest (best quality) appears first.
return (0 if is_recommended else 1, 0 if is_ud else 1, -v.size_bytes)
variants.sort(key = _sort_key)
# Sort by size descending (largest = best quality first).
# Recommended pinning and OOM demotion are handled client-side
# where GPU VRAM info is available.
variants.sort(key = lambda v: -v.size_bytes)
return variants, has_vision

21
studio/frontend/src/components/assistant-ui/model-selector/pickers.tsx
View file

@ -206,7 +206,24 @@ function GgufVariantExpander({
);
}
if (!variants || variants.length === 0) {
const sortedVariants = useMemo(() => {
if (!variants) return variants;
return [...variants].sort((a, b) => {
const aIsRec = a.quant === defaultVariant;
const bIsRec = b.quant === defaultVariant;
if (aIsRec !== bIsRec) return aIsRec ? -1 : 1;
const aGb = a.size_bytes / (1024 ** 3);
const bGb = b.size_bytes / (1024 ** 3);
const aOom = gpuGb != null && gpuGb > 0 && aGb > 0 && checkVramFit(aGb, gpuGb) === "exceeds";
const bOom = gpuGb != null && gpuGb > 0 && bGb > 0 && checkVramFit(bGb, gpuGb) === "exceeds";
if (aOom !== bOom) return aOom ? 1 : -1;
return b.size_bytes - a.size_bytes;
});
}, [variants, defaultVariant, gpuGb]);
if (!sortedVariants || sortedVariants.length === 0) {
return (
<div className="px-5 py-2 text-xs text-muted-foreground">
No GGUF variants found.
@ -224,7 +241,7 @@ function GgufVariantExpander({
<span className="text-[9px] font-medium text-blue-400">Vision</span>
)}
</div>
{variants.map((v) => {
{sortedVariants.map((v) => {
const sizeGb = v.size_bytes / (1024 ** 3);
const fitStatus = gpuGb != null && gpuGb > 0 && sizeGb > 0
? checkVramFit(sizeGb, gpuGb)