local ai

What's Changed Models run on MLX on Apple Silicon by default In this release, on Apple Silicon devices, model architectures supported by the MLX runtime will automatically run on MLX. ollama pull qwen

mlx: match publisher tokenizer semantics Honor pretokenizer stage order, split behavior, Unicode boundaries, added-token normalization, and ranked BPE merges. Handle empty added tokens and empty Metas

**Release:** `v0.34.1‑rc0` (release candidate). **Repository:** `ollama/ollama`. **Key changes:** The release bumps the MLX library version, adds support for `ModelOpt` global scales in Mixture-of-Exp

Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app

**Release Summary – v0.32.15 (GitHub Release)** Version 0.32.15 was published on **19 Aug**, adding a *model metadata cache* to reduce per‑request overhead in Ollama. The release builds on the previou

CUDA: MMVQ nwarps=8 for bs=1 for dense models on DGX Spark Signed-off-by: ynankani ynankani@nvidia.com skip moe experts and allow others based on k geometry (allow only small idle tail) Signed-off-by:

**Ollama v0.32.13 Release (14 Aug)** The release contains a single signed commit (ID 0f25c31) verified with GitHub’s GPG key B5690EEEBB952194. The primary change in this version is the addition of dev

ModelOpt checkpoints apply a float32 global scale to every projection output on top of the per-group quantization scales. Running the multiply and the cast back to the activation dtype as separate eag

v0.32.8 is an Oct 10, 2023 release of the ollama repository on GitHub, following a pre‑release tag v0.32.8‑rc0. The update adds Muse Glimmer support for NVIDIA, AMD and additional platforms, with the

**Ollama – v0.32.5 Release Summary** - Version **v0.32.5** (released 27 Jul at 01:25) is the latest stable release on GitHub, with a signed commit (GPG Key ID B5690EEEBB952194). - The update includes

What's Changed x/create: quantize lm_head at 8-bit in the requested family by @jessegross in #17357 test: harden flaky updater and transfer unit tests by @dhiltgen in #17378 server: fix ps data race o

The **v0.32.2‑rc1** release (commit 4d1b53e, signed with a GPG key) introduces server-side logic to detect download stalls that occur before any data is received. It also removes the stall‑timeout set

This refactors the existing integration tests into 3 priumary groups: fast, release, and library. It also refines some of the release tests to drop some of the older models and pick up newer models, w

**Release v0.32.2‑rc0 (commit de1ce45)** adds support for Compute Capability 10.0 in the Linux “CUDA v12” preset, enabling B200‑class GPUs to use the `cuda_v12` backend even when drivers do not meet t

The search did not return the specific details of the b9947 release. Based on the repository and context available: B9947 is a release of llama.cpp, which enables LLM inference in C/C++ . The release

b9948 is a build release of llama.cpp, an open-source C/C++ project for efficient large language model inference. The project ships continuous build-tagged releases using a build numbering system rath

b9949 is a release build of llama.cpp, the open-source C/C++ inference engine for running large language models locally. llama.cpp releases are published frequently with build versions in the b-series

b9950 is a release of llama.cpp, a C/C++ tool for LLM inference . This build number represents one of the frequent incremental releases from the llama.cpp project, which follows a rapid development cy

Release b9956 is a build version of llama.cpp, an open-source project for LLM inference in C/C++ . The project releases frequently, with multiple releases published in a single day , and b9956 represe

Release b9967 of llama.cpp, an LLM inference project in C/C++, includes an update to the server component allowing it to accept null sampling parameters (PR #25538). This change enables more flexible

The search results do not contain specific information about v0.32.0-rc0. Based on the version numbering and context from Ollama's release patterns, v0.32.0-rc0 is a release candidate for Ollama, a la

llama.cpp is an open-source software library that performs inference on various large language models , and b9934 represents a specific build release in the project's continuous versioning system. The

b9935 is a build release from the llama.cpp project, which implements LLM inference in C/C++. The project doesn't follow traditional release practices, as multiple releases can be published in a singl

llama.cpp b9936 is a continuous build-tagged release from the open-source llama.cpp project , which is an open-source C/C++ inference engine that powers most of the local-AI ecosystem . This release c

The search results do not contain specific details about release b9938. However, based on the context available, b9938 is one of the regular build releases from the llama.cpp project. Llama.cpp releas

Release b9940 of llama.cpp was published on July 9, 2026 , and includes changes related to llama-bench initialization parameters . The release provides pre-built binaries across multiple platforms inc

b9945 is a build-tagged release of llama.cpp, an open-source library that performs inference on large language models and is co-developed alongside the GGML tensor library. The llama.cpp project does

The search results show that b9946 is a specific release build tag from the llama.cpp project, though the exact details of that particular build are not visible in the page content retrieved. Based on

Based on the available information, b9905 is a build-tagged release from the llama.cpp project, which is an open-source C/C++ inference engine that powers most of the local-AI ecosystem . The project

b9908 is a build-tagged release from llama.cpp , the open-source C/C++ inference engine for large language models. llama.cpp is an open-source software library that performs inference on various large

llama.cpp is an open-source software library that performs inference on various large language models , and the project ships continuous build-tagged releases rather than traditional semantic versioni

Based on available information, b9910 is a release tag from the llama.cpp project, an open-source C/C++ implementation for running large language model inference locally on consumer hardware. Llama.cp

b9913 is a build-tagged release from llama.cpp, an open-source software library that performs inference on various large language models. The project does not use traditional semantic versions; instea

The search results don't contain specific details about the b9914 release. Based on the context of llama.cpp releases, b9914 is a build/commit version in the llama.cpp project, an open-source tool for

b9916 is a release of llama.cpp, an open-source C/C++ implementation for LLM inference . The release represents part of the project's rapid development cycle, with binaries available for multiple plat

b9923 is a release build of llama.cpp, an open-source C/C++ project for LLM inference with minimal setup and state-of-the-art performance on various hardware . The specific b9923 build includes binary

Release b9925 of llama.cpp is a version update for the LLM inference in C/C++ project. This build is part of the project's frequent release cycle, which can publish multiple releases in a single day ,

The search results don't provide specific details about release b9929. Based on the available information and the context that llama.cpp releases frequently with tagged versions, b9929 is a specific b

Based on available information, b9931 is a release of llama.cpp, which is an open-source project for large language model inference in C/C++. As a commit-based release from the ggml-org/llama.cpp repo

B9932 is a continuous build-tagged release from the llama.cpp project , an open-source C/C++ inference engine for running large language models locally. llama.cpp performs inference on various large l

b9933 is a continuous build-tagged release of llama.cpp , the C/C++ inference engine for running large language models locally. This release represents an incremental update in llama.cpp's development

b9893 is a release build of llama.cpp with Windows OpenVINO 2026.2.1 support . The llama.cpp project uses continuous build-tagged releases rather than traditional semantic versioning , making b9893 on

Release b9894 of llama.cpp was published on July 7, 2026 , and includes a Vulkan backend fix to check src0 type in GGML_OP_SET_ROWS to avoid failures due to unimplemented f16 support . Llama.cpp is th

Release b9895 of llama.cpp includes a fix for speculative inference out-of-bounds read in ngram-map on prompt shrink, with ~2x performance gains in PP_Speed for FP32, Q4_0 and Q8_0 models. The release

Release b9902 of llama.cpp was released on July 7, 2026 , and includes support for SYCL operations including cross_entropy_loss and cross_entropy_loss_back . The release provides builds across multipl

Ollama v0.31.2-rc1 is a pre-release version released on July 6, 2026. This release includes CI improvements to avoid unbounded parallelism, fixes for CUDA toolkit lookup, updates to cloud documentatio