diff --git a/core/gallery/importers/parakeet-cpp.go b/core/gallery/importers/parakeet-cpp.go
index aa732aa3e..5b758167b 100644
--- a/core/gallery/importers/parakeet-cpp.go
+++ b/core/gallery/importers/parakeet-cpp.go
@@ -108,6 +108,11 @@ func (i *ParakeetCppImporter) Import(details Details) (gallery.ModelConfig, erro
 
 	uri := downloader.URI(details.URI)
 	directGGUF := isParakeetGGUF(filepath.Base(details.URI))
+	// A speaker diarization GGUF is served by the same backend but answers
+	// /v1/audio/diarization, not transcription.
+	if directGGUF && isParakeetDiarGGUF(filepath.Base(details.URI)) {
+		modelConfig.KnownUsecaseStrings = []string{"diarization"}
+	}
 	switch {
 	case uri.LooksLikeURL() && directGGUF:
 		// Direct file URL (e.g. .../resolve/main/tdt_ctc-110m-f16.gguf). The
@@ -128,12 +133,23 @@ func (i *ParakeetCppImporter) Import(details Details) (gallery.ModelConfig, erro
 		// HF repo: collect every parakeet GGUF, pick the preferred quant, and
 		// nest under parakeet-cpp/models/<name>/ so a multi-quant repo doesn't
 		// collide on disk.
-		var ggufFiles []hfapi.ModelFile
+		// Prefer ASR weights: a repo that also ships the diarization model
+		// (mudler/parakeet-cpp-gguf) imports as a transcription model, and the
+		// diarization GGUF is imported by its direct URL. A repo with only
+		// diarization weights imports as a diarization model.
+		var ggufFiles, diarFiles []hfapi.ModelFile
 		for _, f := range details.HuggingFace.Files {
-			if isParakeetGGUF(filepath.Base(f.Path)) {
+			switch base := filepath.Base(f.Path); {
+			case isParakeetDiarGGUF(base):
+				diarFiles = append(diarFiles, f)
+			case isParakeetGGUF(base):
 				ggufFiles = append(ggufFiles, f)
 			}
 		}
+		if len(ggufFiles) == 0 && len(diarFiles) > 0 {
+			ggufFiles = diarFiles
+			modelConfig.KnownUsecaseStrings = []string{"diarization"}
+		}
 		if chosen, ok := pickPreferredGGMLFile(ggufFiles, quants); ok {
 			target := filepath.Join("parakeet-cpp", "models", name, filepath.Base(chosen.Path))
 			cfg.Files = append(cfg.Files, gallery.File{
@@ -176,5 +192,14 @@ func isParakeetGGUF(name string) bool {
 			return true
 		}
 	}
-	return false
+	return isParakeetDiarGGUF(name)
+}
+
+// isParakeetDiarGGUF reports whether name is the parakeet.cpp speaker
+// diarization GGUF (nemotron-3-diarization-<quant>.gguf). Matched by its
+// published name only, so diarization weights for other backends are not
+// claimed.
+func isParakeetDiarGGUF(name string) bool {
+	lower := strings.ToLower(name)
+	return strings.HasSuffix(lower, ".gguf") && strings.Contains(lower, "nemotron-3-diarization")
 }
diff --git a/core/gallery/importers/parakeet-cpp_test.go b/core/gallery/importers/parakeet-cpp_test.go
index 4aa87c411..8636c929d 100644
--- a/core/gallery/importers/parakeet-cpp_test.go
+++ b/core/gallery/importers/parakeet-cpp_test.go
@@ -50,6 +50,11 @@ var _ = Describe("ParakeetCppImporter", func() {
 			Expect(imp.Match(d)).To(BeTrue())
 		})
 
+		It("matches a direct URL to the diarization GGUF", func() {
+			d := parakeetDetails("https://huggingface.co/mudler/parakeet-cpp-gguf/resolve/main/nemotron-3-diarization-q8_0.gguf", `{}`)
+			Expect(imp.Match(d)).To(BeTrue())
+		})
+
 		It("does NOT claim a generic llama-style GGUF", func() {
 			d := parakeetDetails("huggingface://someorg/some-llm-gguf", `{}`,
 				hfapi.ModelFile{Path: "llama-3-8b-instruct-q4_k_m.gguf"},
@@ -66,6 +71,43 @@ var _ = Describe("ParakeetCppImporter", func() {
 	})
 
 	Context("import (Import)", func() {
+		It("imports the diarization GGUF as a diarization model", func() {
+			d := parakeetDetails("https://huggingface.co/mudler/parakeet-cpp-gguf/resolve/main/nemotron-3-diarization-q8_0.gguf",
+				`{"name":"nemotron-diarization"}`)
+			cfg, err := imp.Import(d)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(cfg.ConfigFile).To(ContainSubstring("backend: parakeet-cpp"))
+			Expect(cfg.ConfigFile).To(ContainSubstring("diarization"))
+			Expect(cfg.ConfigFile).ToNot(ContainSubstring("transcript"))
+			Expect(cfg.Files).To(HaveLen(1))
+			Expect(cfg.Files[0].Filename).To(HaveSuffix("nemotron-3-diarization-q8_0.gguf"))
+		})
+
+		It("keeps picking ASR weights from a repo that also ships the diarization model", func() {
+			d := parakeetDetails("huggingface://mudler/parakeet-cpp-gguf", `{"name":"parakeet-110m"}`,
+				hfapi.ModelFile{Path: "nemotron-3-diarization-f16.gguf", URL: "https://hf/diar-f16", SHA256: "ddd"},
+				hfapi.ModelFile{Path: "tdt_ctc-110m-f16.gguf", URL: "https://hf/f16", SHA256: "aaa"},
+				hfapi.ModelFile{Path: "nemotron-3-diarization-q8_0.gguf", URL: "https://hf/diar-q8", SHA256: "eee"},
+			)
+			cfg, err := imp.Import(d)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(cfg.Files).To(HaveLen(1))
+			Expect(cfg.Files[0].URI).To(Equal("https://hf/f16"))
+			Expect(cfg.ConfigFile).To(ContainSubstring("transcript"))
+		})
+
+		It("imports a diarization-only repo as a diarization model", func() {
+			d := parakeetDetails("huggingface://someone/diar-gguf", `{"name":"diar"}`,
+				hfapi.ModelFile{Path: "nemotron-3-diarization-f16.gguf", URL: "https://hf/diar-f16", SHA256: "ddd"},
+				hfapi.ModelFile{Path: "nemotron-3-diarization-q8_0.gguf", URL: "https://hf/diar-q8", SHA256: "eee"},
+			)
+			cfg, err := imp.Import(d)
+			Expect(err).ToNot(HaveOccurred())
+			Expect(cfg.Files).To(HaveLen(1))
+			Expect(cfg.Files[0].URI).To(Equal("https://hf/diar-q8"), "default quant ladder picks q8_0 before f16")
+			Expect(cfg.ConfigFile).To(ContainSubstring("diarization"))
+		})
+
 		It("picks the default quant (q4_k) from a multi-quant HF repo", func() {
 			d := parakeetDetails("huggingface://mudler/parakeet-cpp-gguf", `{"name":"parakeet-110m"}`,
 				hfapi.ModelFile{Path: "tdt_ctc-110m-f16.gguf", URL: "https://hf/f16", SHA256: "aaa"},
diff --git a/docs/content/features/audio-diarization.md b/docs/content/features/audio-diarization.md
index cb8f866dd..3bfde1aef 100644
--- a/docs/content/features/audio-diarization.md
+++ b/docs/content/features/audio-diarization.md
@@ -160,15 +160,13 @@ curl http://localhost:8080/v1/audio/diarization \
 
 ## Backend setup - parakeet.cpp (Nemotron-3-Diarization)
 
-The [parakeet-cpp backend]({{%relref "features/audio-to-text#using-the-parakeet-cpp-backend" %}}) runs [nvidia/Nemotron-3-Diarization](https://huggingface.co/nvidia/Nemotron-3-Diarization). Convert the checkpoint to GGUF with parakeet.cpp's converter (Q8_0 is 109 MB and gives the same segments as F32):
+The [parakeet-cpp backend]({{%relref "features/audio-to-text#using-the-parakeet-cpp-backend" %}}) runs [nvidia/Nemotron-3-Diarization](https://huggingface.co/nvidia/Nemotron-3-Diarization). GGUF weights are published in [`mudler/parakeet-cpp-gguf`](https://huggingface.co/mudler/parakeet-cpp-gguf): F16 (191 MB) and Q8_0 (104 MB) both give the same segments as NeMo. Import one directly:
 
 ```bash
-python scripts/convert_parakeet_to_gguf.py \
-    --model nvidia/Nemotron-3-Diarization --dtype q8_0 \
-    --output nemotron-3-diarization-q8_0.gguf
+local-ai models import https://huggingface.co/mudler/parakeet-cpp-gguf/resolve/main/nemotron-3-diarization-q8_0.gguf
 ```
 
-A diarization-only model:
+Or configure it by hand, as a diarization-only model:
 
 ```yaml
 name: nemotron-diarization
diff --git a/docs/content/features/audio-to-text.md b/docs/content/features/audio-to-text.md
index 5b3937344..f927cc121 100644
--- a/docs/content/features/audio-to-text.md
+++ b/docs/content/features/audio-to-text.md
@@ -207,7 +207,7 @@ options:
 
 ### Speaker labels
 
-Attach a speaker diarization model with the `diar_model` option and each transcript segment carries a `speaker` (`"0"`, `"1"`, ... in order of first appearance). Segments split wherever the speaker changes, on top of the punctuation split. The model is NVIDIA Nemotron-3-Diarization, converted with parakeet.cpp's converter; see [Speaker Diarization]({{< relref "audio-diarization.md" >}}) for the conversion and for the `/v1/audio/diarization` endpoint the same model serves.
+Attach a speaker diarization model with the `diar_model` option and each transcript segment carries a `speaker` (`"0"`, `"1"`, ... in order of first appearance). Segments split wherever the speaker changes, on top of the punctuation split. The model is NVIDIA Nemotron-3-Diarization, published as `nemotron-3-diarization-f16.gguf` and `nemotron-3-diarization-q8_0.gguf` in [`mudler/parakeet-cpp-gguf`](https://huggingface.co/mudler/parakeet-cpp-gguf); see [Speaker Diarization]({{< relref "audio-diarization.md" >}}) for the conversion and for the `/v1/audio/diarization` endpoint the same model serves.
 
 ```yaml
 name: parakeet-speakers