What's Changed

• /api/show will now include model capabilities such as vision
• Fixed certain out-of-memory errors that would occur with parallel requests with Gemma 3
• Gemma 3 will now properly understand and output certain multilingual characters
• Fixed context shifting issues with models using the DeepSeek architecture
• Fixed issues with 0.6.3 where Gemma 3's output quality would worsen after 512 or 1024 tokens
• Added AMD RDNA4 support on Linux

New Contributors

• @saman-amd made their first contribution in #9878
• @leandroBorgesFerreira made their first contribution in #10042
• @Abyss-c0re made their first contribution in #9955
• @uggrock made their first contribution in #9983
• @IsAurora6 made their first contribution in #10057

Full Changelog: v0.6.3...v0.6.4