From e97492369888f5311e4d1f3beb325a36bbed70e9 Mon Sep 17 00:00:00 2001
From: Xuan-Son Nguyen <son@huggingface.co>
Date: Mon, 13 Apr 2026 22:28:17 +0200
Subject: [PATCH] docs: listing qwen3-asr and qwen3-omni as supported (#21857)

* docs: listing qwen3-asr and qwen3-omni as supported

* nits
---
 docs/multimodal.md  | 9 +++++++++
 tools/mtmd/tests.sh | 1 +
 2 files changed, 10 insertions(+)

diff --git a/docs/multimodal.md b/docs/multimodal.md
index 89b9574f0a..33d1df33c3 100644
--- a/docs/multimodal.md
+++ b/docs/multimodal.md
@@ -114,6 +114,10 @@ NOTE: some models may require large context window, for example: `-c 8192`
 
 # Mistral's Voxtral
 (tool_name) -hf ggml-org/Voxtral-Mini-3B-2507-GGUF
+
+# Qwen3-ASR
+(tool_name) -hf ggml-org/Qwen3-ASR-0.6B-GGUF
+(tool_name) -hf ggml-org/Qwen3-ASR-1.7B-GGUF
 ```
 
 **Mixed modalities**:
@@ -124,6 +128,11 @@ NOTE: some models may require large context window, for example: `-c 8192`
 (tool_name) -hf ggml-org/Qwen2.5-Omni-3B-GGUF
 (tool_name) -hf ggml-org/Qwen2.5-Omni-7B-GGUF
 
+# Qwen3 Omni
+# Capabilities: audio input, vision input
+(tool_name) -hf ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF
+(tool_name) -hf ggml-org/Qwen3-Omni-30B-A3B-Thinking-GGUF
+
 # Gemma 4
 # Capabilities: audio input, vision input
 (tool_name) -hf ggml-org/gemma-4-E2B-it-GGUF
diff --git a/tools/mtmd/tests.sh b/tools/mtmd/tests.sh
index eb01986164..5da48d61bf 100755
--- a/tools/mtmd/tests.sh
+++ b/tools/mtmd/tests.sh
@@ -98,6 +98,7 @@ add_test_audio  "ggml-org/Qwen2.5-Omni-3B-GGUF:Q4_K_M"
 add_test_audio  "ggml-org/Voxtral-Mini-3B-2507-GGUF:Q4_K_M"
 add_test_audio  "ggml-org/LFM2-Audio-1.5B-GGUF:Q8_0"
 add_test_audio  "ggml-org/gemma-4-E2B-it-GGUF:Q8_0" --jinja
+add_test_audio  "ggml-org/Qwen3-ASR-0.6B-GGUF:Q8_0"
 
 # to test the big models, run: ./tests.sh big
 if [ "$RUN_BIG_TESTS" = true ]; then