Ollama

PatchBot will keep your Discord channel up-to-date on all the latest Ollama patch notes.

Servers

636

Gamers

120,050

Game details

Description This AI tool simplifies the process of running machine learning models locally, enabling developers to easily deploy and interact with various models without extensive setup. Its user-friendly interface streamlines the integration of AI into applications.
Release Date Jul 8, 2023

Latest updates

PatchBot BOT 1 day ago

v0.32.6

What's Changed

Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically
/v1/chat/completions streaming now matches OpenAI's wire format: role only on the first chunk, finish_reason on its own chunk, and usage in a separate chunk with stream_options.include_usage.
Truncated OpenAI responses now report finish_reason: "length" instead of "tool_calls". ...

Git tag

v0.32.6

PatchBot BOT 1 week ago

v0.32.5

What's Changed

Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna.

Git tag

v0.32.5

PatchBot BOT 1 week ago

v0.32.4

What's Changed

Support Laguna on Apple GPUs via the MLX engine
Quantize draft-model output heads at the requested type when creating speculative-decoding drafts.
Fixed Qwen3 MoE decoding for differently-quantized experts, plus faster packed gate/up projection (~4–9% on M5 Max).

Git tag

v0.32.4

PatchBot BOT 2 weeks ago

v0.32.3

What's Changed

Fixed model downloads that stall before sending data.
Improved integrations: restored Claude Code Channels, fixed Anthropic thinking streams, and made Hermes Desktop respect --force-build.
Expanded GPU support with CUDA on Windows ARM64, B200 support through CUDA 12, and lower memory use on Linux CUDA/ROCm iGPUs.
Added chat, thinking, and tool calling support for Laguna 2.1 models, including a Metal inference fix. ...

Git tag

v0.32.3

PatchBot BOT 3 weeks ago

v0.32.1

What's Changed

Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations
Fixed a recurrent MLX model cache leak that could increase memory use across requests, and improved cache snapshot performance
MLX text model loading now respects OLLAMA_LOAD_TIMEOUT
Agent web search and fetch now tell users to run ollama signin when authentication is required ...

Git tag

v0.32.1

PatchBot BOT 3 weeks ago

v0.32.0

What's Changed

New interactive agent experience: running ollama now launches an agent to help you code and delegate work

❯ ollama
Ollama 0.32.0
▸ Chat, Code, & Work (glm-5.2:cloud)
    Chat with models, code, search the web, and delegate real work

Renamed the Codex App integration to ChatGPT: use ollama launch chatgpt (and --restore to return to your usual ChatGPT profile) ...

Git tag

v0.32.0

PatchBot BOT 1 day ago

v0.32.6

What's Changed

Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically
/v1/chat/completions streaming now matches OpenAI's wire format: role only on the first chunk, finish_reason on its own chunk, and usage in a separate chunk with stream_options.include_usage.
Truncated OpenAI responses now report finish_reason: "length" instead of "tool_calls". ...

Git tag

v0.32.6

PatchBot BOT 2 days ago

v0.32.6

What's Changed

Qwen3.5 is faster on Apple GPUs: the MLX engine now uses the model's MTP head for speculative decoding automatically
/v1/chat/completions streaming now matches OpenAI's wire format: role only on the first chunk, finish_reason on its own chunk, and usage in a separate chunk with stream_options.include_usage.
Truncated OpenAI responses now report finish_reason: "length" instead of "tool_calls". ...

Git tag

v0.32.6-rc0

PatchBot BOT 1 week ago

v0.32.5

What's Changed

Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna.

Git tag

v0.32.5

PatchBot BOT 1 week ago

v0.32.5

What's Changed

mlx update by @dhiltgen in #17397

Git tag

v0.32.5-rc0

PatchBot BOT 1 week ago

v0.32.4

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 on scheduler loaded map by @dhiltgen in #17376 ...

Git tag

v0.32.4

PatchBot BOT 1 week ago

v0.32.4

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 on scheduler loaded map by @dhiltgen in #17376 ...

Git tag

v0.32.4-rc0

FANTASY LIFE i: The Girl Who Steals Time