diff --git a/CHANGELOG.md b/CHANGELOG.md
index d713d58908..795c353c89 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -25,6 +25,7 @@ _Living section — bullets land here as PRs merge into `release/v3.8.47` (paral
 - **feat(providers):** custom models now support a manual **Context Window Override** so an operator can correct a provider's misreported context length (e.g. reports 1M when the real limit is 128K) instead of the model silently getting dropped from combo routing once the wrong value lands in the catalog ([#4125](https://github.com/diegosouzapw/OmniRoute/issues/4125) — thanks @rucciva). Reuses the existing Feature-5004 `model_context_overrides` table (`source: "manual"`) — already the priority-0 source `getModelContextLimit()` (the function combo's context-window filter calls) reads ahead of the models.dev/registry/static catalog — so no new resolver logic was needed, only the missing write path: `PUT /api/provider-models` now accepts an optional `contextWindowOverride` (number to set, `null` to clear), `GET` surfaces the current value back on each custom-model row, and the provider detail page's custom-model edit form gained a Context Window Override field + badge. Regression guard: `tests/unit/provider-models-context-window-override-4125.test.ts`.
 - **fix(providers):** register OpenRouter as a rerank provider so `openrouter/cohere/rerank-*` models resolve instead of erroring `Invalid rerank model` (#6574 — thanks @rafpigna)
 - **fix(api):** `HEAD` requests no longer hang until client timeout on any route — valid, unknown, authed, or unauthed ([#6400](https://github.com/diegosouzapw/OmniRoute/issues/6400)), broader follow-up to the route-specific #6517 (`/v1/models`). Root cause: Next.js 16's App Router _route-handler_ pipeline (`next/dist/server/send-response.js`) correctly skips piping a `Response` body for `HEAD`, but its _page_-rendering pipeline (`next/dist/server/pipe-readable.js` → `pipeToNodeResponse`, used for every app-router page/layout render — including the `not-found` boundary any unmatched path falls through to) has no such check and always streams the full rendered body regardless of method; combined with Node's default keep-alive framing this left some clients unsure whether the (implicitly bodyless) `HEAD` response had actually finished. A new `scripts/dev/head-response-guard.cjs`, wired into both the dev/start custom server (`scripts/dev/run-next.mjs`) and the packaged standalone server (`scripts/dev/standalone-server-ws.mjs`) at the same tier as the existing `http-method-guard.cjs`/`peer-stamp.mjs` wrappers, discards any body bytes written for a `HEAD` request and forces `Connection: close` once `.end()` is called — independent of route existence or auth state, satisfying RFC 9110 §9.3.2. Regression guard: `tests/unit/head-request-closes-6400.test.ts`.
+- **feat(dashboard):** Provider Quota page (`Dashboard → Quota`) fills horizontal whitespace before stacking vertically ([#3520](https://github.com/diegosouzapw/OmniRoute/issues/3520)) — `QuotaCardGrid` previously stacked every provider group in a single vertical `flex flex-col`, and each group's own card grid didn't go multi-column until `md` (`grid-cols-1 md:grid-cols-2 xl:grid-cols-3 2xl:grid-cols-4`). Provider groups now flow into a 2-column CSS multi-column layout on very wide (`2xl`) screens instead of an unconditional vertical stack, and each group's card grid starts at 2 columns immediately (`grid-cols-2 md:grid-cols-3 xl:grid-cols-4`), reaching higher density sooner on narrower-but-not-mobile viewports. Regression guard: `tests/unit/quota-card-grid-horizontal-layout.test.ts` (thanks @gdevenyi).
 
 ### 🐛 Bug Fixes
 
diff --git a/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/QuotaCardGrid.tsx b/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/QuotaCardGrid.tsx
index b8cc040af9..dbf1c253fd 100644
--- a/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/QuotaCardGrid.tsx
+++ b/src/app/(dashboard)/dashboard/usage/components/ProviderLimits/QuotaCardGrid.tsx
@@ -47,16 +47,16 @@ export default function QuotaCardGrid({
   }
 
   return (
-    <div className="flex flex-col gap-6">
+    <div className="columns-1 2xl:columns-2 gap-6 [column-fill:_balance]">
       {[...groups.entries()].map(([provider, conns]) => (
-        <div key={provider} className="flex flex-col gap-3">
+        <div key={provider} className="flex flex-col gap-3 break-inside-avoid mb-6">
           <h3 className="text-sm font-semibold text-text-main flex items-center gap-2">
             {providerLabels[provider] || provider}
             <span className="text-xs font-normal text-text-muted">
               ({conns.length} account{conns.length !== 1 ? "s" : ""})
             </span>
           </h3>
-          <div className="grid grid-cols-1 md:grid-cols-2 xl:grid-cols-3 2xl:grid-cols-4 gap-3">
+          <div className="grid grid-cols-2 md:grid-cols-3 xl:grid-cols-4 gap-3">
             {conns.map((conn) => (
               <QuotaCard
                 key={conn.id}
diff --git a/tests/unit/quota-card-grid-horizontal-layout.test.ts b/tests/unit/quota-card-grid-horizontal-layout.test.ts
new file mode 100644
index 0000000000..9966034ba9
--- /dev/null
+++ b/tests/unit/quota-card-grid-horizontal-layout.test.ts
@@ -0,0 +1,120 @@
+// #3520 — Provider Quota page should use horizontal whitespace better.
+//
+// QuotaCardGrid previously stacked provider groups vertically via a single
+// `flex flex-col` container and kept cards to a conservative 1/2/3/4-column
+// breakpoint ladder starting at `grid-cols-1`. This regression guard asserts
+// the shipped JSX structure and grouping logic directly:
+//  1. Grouping still produces one header per distinct provider with the
+//     correct account count ("N account(s)").
+//  2. The per-group card grid starts multi-column (`grid-cols-2`), not
+//     single-column, so cards fill horizontal space sooner.
+//  3. Provider groups themselves flow into multiple columns on wide screens
+//     (`columns-*`) instead of an unconditional vertical `flex flex-col`
+//     stack.
+//
+// Note: QuotaCardGrid's sibling QuotaCard pulls in next/image + provider-icon
+// resolution that only works inside the real Next.js runtime, so this file
+// exercises the two testable seams directly instead of full SSR-rendering the
+// tree: (a) the pure grouping function extracted below, mirroring the
+// component's own grouping logic, and (b) the literal className contract of
+// the component's JSX (static string literals, not derived at runtime),
+// parsed from source via the TypeScript compiler API so the assertions track
+// the real shipped markup rather than a hand-copied string.
+
+import { test } from "node:test";
+import assert from "node:assert/strict";
+import fs from "node:fs";
+import path from "node:path";
+import ts from "typescript";
+
+const COMPONENT_PATH = path.resolve(
+  import.meta.dirname,
+  "../../src/app/(dashboard)/dashboard/usage/components/ProviderLimits/QuotaCardGrid.tsx"
+);
+
+function groupByProvider<T extends { provider: string }>(connections: T[]): Map<string, T[]> {
+  const groups = new Map<string, T[]>();
+  for (const conn of connections) {
+    const list = groups.get(conn.provider) ?? [];
+    list.push(conn);
+    groups.set(conn.provider, list);
+  }
+  return groups;
+}
+
+test("QuotaCardGrid (#3520) — groups connections by provider with correct counts", () => {
+  const groups = groupByProvider([
+    { id: "conn-a1", provider: "openai" },
+    { id: "conn-a2", provider: "openai" },
+    { id: "conn-b1", provider: "anthropic" },
+  ]);
+  assert.deepEqual([...groups.keys()], ["openai", "anthropic"]);
+  assert.equal(groups.get("openai")!.length, 2);
+  assert.equal(groups.get("anthropic")!.length, 1);
+});
+
+/**
+ * Extract the string literal passed to `className={...}` (or `className="..."`)
+ * for every JSX `<div>` opening element in the component's `return (...)` JSX,
+ * in source order, via the TypeScript compiler API (not a hand-rolled regex —
+ * tracks the real AST so it can't be fooled by comments/whitespace).
+ */
+function extractDivClassNames(sourcePath: string): string[] {
+  const sourceText = fs.readFileSync(sourcePath, "utf8");
+  const sourceFile = ts.createSourceFile(
+    sourcePath,
+    sourceText,
+    ts.ScriptTarget.Latest,
+    true,
+    ts.ScriptKind.TSX
+  );
+  const classNames: string[] = [];
+
+  function visit(node: ts.Node) {
+    if (ts.isJsxOpeningElement(node) || ts.isJsxSelfClosingElement(node)) {
+      const tagName = node.tagName.getText(sourceFile);
+      if (tagName === "div") {
+        for (const attr of node.attributes.properties) {
+          if (ts.isJsxAttribute(attr) && attr.name.getText(sourceFile) === "className") {
+            const init = attr.initializer;
+            if (init && ts.isStringLiteral(init)) {
+              classNames.push(init.text);
+            } else if (
+              init &&
+              ts.isJsxExpression(init) &&
+              init.expression &&
+              ts.isStringLiteral(init.expression)
+            ) {
+              classNames.push(init.expression.text);
+            }
+          }
+        }
+      }
+    }
+    ts.forEachChild(node, visit);
+  }
+  visit(sourceFile);
+  return classNames;
+}
+
+test("QuotaCardGrid (#3520) — outer container flows groups into multiple columns, not a single vertical stack", () => {
+  const [outerClassName] = extractDivClassNames(COMPONENT_PATH);
+  assert.ok(outerClassName, "expected the component to render an outer <div className=...>");
+  assert.match(outerClassName, /\bcolumns-/);
+  assert.notEqual(outerClassName, "flex flex-col gap-6");
+});
+
+test("QuotaCardGrid (#3520) — per-group card grid starts multi-column (grid-cols-2), not single-column", () => {
+  const classNames = extractDivClassNames(COMPONENT_PATH);
+  const cardGridClassName = classNames.find(
+    (c) => /\bgrid\b/.test(c) && /grid-cols-/.test(c)
+  );
+  assert.ok(cardGridClassName, "expected to find the per-group card grid's className");
+  assert.match(cardGridClassName!, /\bgrid-cols-2\b/);
+  assert.doesNotMatch(cardGridClassName!, /\bgrid-cols-1\b/);
+});
+
+test("QuotaCardGrid (#3520) — early-returns null when there are no connections", () => {
+  const sourceText = fs.readFileSync(COMPONENT_PATH, "utf8");
+  assert.match(sourceText, /if\s*\(\s*connections\.length\s*===\s*0\s*\)\s*return\s*null;/);
+});