From: Xuan-Son Nguyen <redacted>
Date: Sun, 12 Apr 2026 14:29:03 +0000 (+0200)
Subject: mtmd: add gemma 4 test (vision + audio) [no ci] (#21806)
X-Git-Tag: upstream/0.0.10438~1671
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=aa4695c5e5bf0abda8942c08e94cb804a7ea0347;p=pkg%2Fggml%2Fsources%2Fllama.cpp

mtmd: add gemma 4 test (vision + audio) [no ci] (#21806)

* mtmd: add gemma 4 test (vision + audio)

* add to docs
---

diff --git a/docs/multimodal.md b/docs/multimodal.md
index f849eb969..89b9574f0 100644
--- a/docs/multimodal.md
+++ b/docs/multimodal.md
@@ -94,6 +94,11 @@ NOTE: some models may require large context window, for example: `-c 8192`
 # Moondream2 20250414 version
 (tool_name) -hf ggml-org/moondream2-20250414-GGUF
 
+# Gemma 4
+(tool_name) -hf ggml-org/gemma-4-E2B-it-GGUF
+(tool_name) -hf ggml-org/gemma-4-E4B-it-GGUF
+(tool_name) -hf ggml-org/gemma-4-26B-A4B-it-GGUF
+(tool_name) -hf ggml-org/gemma-4-31B-it-GGUF
 ```
 
 **Audio models**:
@@ -118,6 +123,11 @@ NOTE: some models may require large context window, for example: `-c 8192`
 # Capabilities: audio input, vision input
 (tool_name) -hf ggml-org/Qwen2.5-Omni-3B-GGUF
 (tool_name) -hf ggml-org/Qwen2.5-Omni-7B-GGUF
+
+# Gemma 4
+# Capabilities: audio input, vision input
+(tool_name) -hf ggml-org/gemma-4-E2B-it-GGUF
+(tool_name) -hf ggml-org/gemma-4-E4B-it-GGUF
 ```
 
 ## Finding more models:
diff --git a/tools/mtmd/tests.sh b/tools/mtmd/tests.sh
index 651f7a627..eb0198616 100755
--- a/tools/mtmd/tests.sh
+++ b/tools/mtmd/tests.sh
@@ -91,11 +91,13 @@ add_test_vision "ggml-org/LightOnOCR-1B-1025-GGUF:Q8_0"
 add_test_vision "ggml-org/DeepSeek-OCR-GGUF:Q8_0" -p "Free OCR." --chat-template deepseek-ocr
 add_test_vision "ggml-org/dots.ocr-GGUF:Q8_0" -p "OCR"
 add_test_vision "ggml-org/HunyuanOCR-GGUF:Q8_0" -p "OCR"
+add_test_vision "ggml-org/gemma-4-E2B-it-GGUF:Q8_0" --jinja
 
 add_test_audio  "ggml-org/ultravox-v0_5-llama-3_2-1b-GGUF:Q8_0"
 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
 
 # to test the big models, run: ./tests.sh big
 if [ "$RUN_BIG_TESTS" = true ]; then