Models & Labs
Llama.cpp Adds Vision Support with MiniMax-M3
llama.cpp Releaseshigh confidence
Why it matters
- →Integrating vision support expands llama.cpp's capabilities beyond text processing.
- →The update optimizes performance with GPU and CPU operations, enhancing efficiency.
- →This positions llama.cpp to handle more complex, multi-modal tasks in the future.
Llama.cpp has released an update adding preliminary support for the MiniMax-M3 model, enhancing its capabilities with vision support. The update leverages existing components from MiniMax-M2, including per-head QK-norm and partial rotary, while introducing GPU and CPU operations for improved performance. Sparse attention is not yet available, but the update significantly speeds up processing for long contexts. This positions llama.cpp to expand its applications into vision tasks, moving beyond its previous text-only focus.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
What happened next
- 1llama.cpp adds MiniMax model support
llama.cpp Releases · August 16, 2026 · Same story
- 2llama.cpp adds vision target support for DFlash/Dspark
llama.cpp Releases · September 24, 2026 · Same story
Follow this story
Open the full story →llama.cpp b10058 release enhances Vulkan support
3 developments
- Jul 19 · llama.cpp Releases
llama.cpp b10058 release enhances Vulkan support - Jul 23 · llama.cpp Releases
llama.cpp Adds WebGPU Depthwise Conv2D Kernel↳ llama.cpp adds a WebGPU Depthwise Conv2D kernel ported from Vulkan - Jul 27 · llama.cpp Releases
Llama.cpp Adds Vision Support with MiniMax-M3 (This article)↳ llama.cpp adds preliminary MiniMax-M3 vision support with per-head QK-norm and partial rotary
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12398 optimizes Vulkan Flash Attention for AMD
This release targets the persistent performance gap on AMD hardware by optimizing Vulkan Flash Attention specifically for RDNA3 and RDNA4 architectures. The changes include reducing shared memory usage through buffer reuse and fixing critical stability issues like NVIDIA hangs and sparse FA underflow bugs. While there are no new model architectures, these low-level shader optimizations directly translate to faster inference speeds for local users on modern AMD GPUs. It is a quiet but necessary engineering update that tightens the ecosystem for non-NVIDIA accelerators.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12399 adds ROCm 10 and CUDA 13 builds
This release quietly extends llama.cpp’s hardware support to the latest NVIDIA and AMD stacks. By shipping binaries for CUDA 13.5 and ROCm 10.0, it ensures users on cutting-edge GPUs don't have to compile from source to get performance gains. The Vulkan build also fixes header inclusion issues that previously broke compilation on some Linux distributions. It’s a maintenance update rather than a feature leap, but it keeps the local inference runtime compatible with the fastest consumer and datacenter hardware available today.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12400 release with CUDA 13 and ROCm 10
This is a routine maintenance release for llama.cpp that quietly extends hardware support to the latest NVIDIA and AMD stacks. By adding CUDA 13.5 and ROCm 10.0 binaries, it ensures local inference remains viable on cutting-edge GPUs without waiting for community forks. The build also includes OpenVINO and SYCL variants, reinforcing its role as the universal runtime for diverse accelerators. While no new model architectures are introduced, this update keeps the toolchain compatible with modern driver ecosystems.
llama.cpp Releases
More in Models & Labs
© GitHub ChangelogModels & Labscoding
Gemini 4 Hydrogen arrives in GitHub Copilot
Google’s latest Flash model is now generally available in GitHub Copilot, targeting agentic coding and multistep workflows. It offers improved instruction following over Gemini 3.8 Flash and is billed at provider list pricing under usage-based billing. The rollout is gradual across Visual Studio Code, JetBrains IDEs, and other platforms. Administrators can manage access through model policies in Copilot settings.
GitHub Changelog
© TechCrunch AIModels & Labsproductivity
ElevenLabs launches ElevenAI for teams
ElevenLabs is moving beyond voice synthesis into the crowded meeting intelligence space with ElevenAI. The app merges transcription, dictation across 90+ languages, and agent-driven follow-ups like drafting emails directly from conversation context. This positions their $22B valuation engine as a central knowledge hub for enterprises, aiming to replace standalone notetakers. It’s a strategic play to lock teams into their ecosystem using the recently launched v3 Scribe models.
TechCrunch AI
© TechCrunch AIModels & Labsmodels
Google deploys Gemini 4 Hydrogen for faster Search
Google is quietly shifting its search infrastructure by replacing older fast models with Gemini 4 Hydrogen, a tier designed specifically for speed and cost-efficiency rather than raw reasoning power. This model completes tasks 2.5 times faster than its predecessor while beating the more powerful Argon on specific intelligence benchmarks, proving that specialized efficiency can outperform brute force in high-volume workflows. By integrating this into Search's fan-out technique, Google now breaks down complex queries into subqueries with greater precision and speed, delivering richer visual responses without the latency of heavier models. This marks a strategic pivot toward agentic execution layers within consumer search, making AI Mode feel snappier for everyday multi-part questions.
TechCrunch AI