https://cybertoolchain.io/tools/ollama New releases and features in Ollama, tracked by The Cyber Toolchain. en Sat, 15 Aug 2026 19:41:23 GMT https://github.com/ollama/ollama/releases/tag/v0.32.14 https://github.com/ollama/ollama/releases/tag/v0.32.14 Sat, 15 Aug 2026 19:41:23 GMT Ollama v0.32.14 adds WebP image transcoding for vision models and tolerates non-leading system messages in Qwen. • Automatically transcodes WebP image payloads to PNG before forwarding to llama-server, enabling WebP support for vision model integrations alongside existing JPG and PNG formats. • Qwen renderer now passes non-leading system messages through the raw ChatML path instead of returning an HTTP 500, allowing coding clients that inject runtime system prompts mid-conversation to function correctly. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.13 https://github.com/ollama/ollama/releases/tag/v0.32.13 Fri, 14 Aug 2026 19:16:07 GMT Ollama v0.32.13 adds Qwen3.8 developer-instruction support, folding leading system/developer prefixes into a single system turn. • Adds Qwen3.8 support for developer instructions: leading system/developer instruction prefixes sent by OpenAI-compatible coding agents are folded into a single system turn before Qwen3.8 validation, preserving instruction precedence without affecting Qwen3.5 or other renderers. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.12 https://github.com/ollama/ollama/releases/tag/v0.32.12 Fri, 14 Aug 2026 16:37:00 GMT Ollama v0.32.12 adds Qwen3.8 27B support with an Apple Silicon MLX-optimized variant. • Adds `qwen3.8:27b` model, with performance gains across coding, research, and long-horizon agentic tasks, runnable via `ollama run qwen3.8:27b`. • Adds `qwen3.8:27b-mlx` variant optimized for maximum performance and output quality on Apple Silicon devices, runnable via `ollama run qwen3.8:27b-mlx`. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.11 https://github.com/ollama/ollama/releases/tag/v0.32.11 Fri, 14 Aug 2026 01:22:12 GMT Ollama v0.32.11 adds DeepSeek Harness and Muse Code integrations and brings web search to the OpenAI Responses API. • Adds `ollama launch dsh` to integrate DeepSeek Harness, DeepSeek's open-source agent harness. • Adds `ollama launch muse` to integrate Muse Code, Meta's agentic coding CLI. • Adds support for the Nemotron 3.5 prompt layout, selecting the correct parser and renderer from its checkpoint template. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/blob/main/docs/api.md https://github.com/ollama/ollama/blob/main/docs/api.md Wed, 12 Aug 2026 10:29:44 GMT Ollama API docs add a push-a-blob endpoint. • New 'push a blob' API operation documented in the Ollama API reference. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.9 https://github.com/ollama/ollama/releases/tag/v0.32.9 Tue, 11 Aug 2026 13:23:33 GMT Ollama v0.32.9 adds NVIDIA Nemotron 3.5 Lightning (30B MoE) with native MLX support and speculative decoding via built-in draft model. • Adds `nemotron-3.5-lightning`, an NVIDIA 30B mixture-of-experts model with 3B active parameters, runnable via `ollama run nemotron-3.5-lightning`. • Adds the Nemotron 3 architecture to the MLX backend, including Mamba2/recurrent layers, MoE routing, and quantized NVFP4/MXFP8 expert paths with Metal-optimized block-mapped kernels. • Serves Nemotron 3's multi-token prediction head as a built-in self-draft speculator, enabling speculative decoding without a separate draft model. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.8 https://github.com/ollama/ollama/releases/tag/v0.32.8 Mon, 10 Aug 2026 23:49:29 GMT Ollama v0.32.8 adds Muse Glimmer model support across NVIDIA, AMD, and all platforms for local coding agents and personal assistants. • Adds `ollama run muse-glimmer` to download and run the Muse Glimmer model locally on NVIDIA, AMD, and additional platforms. • Adds `ollama launch claude --model muse-glimmer` to run Muse Glimmer with Claude Code as a local coding agent. • Adds `ollama launch pi --model muse-glimmer` to run Muse Glimmer with the Pi coding agent integration. • Adds `ollama launch openclaw --model muse-glimmer` and `ollama launch hermes --model muse-glimmer` to power personal assistant frameworks locally. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.7 https://github.com/ollama/ollama/releases/tag/v0.32.7 Mon, 10 Aug 2026 10:49:15 GMT Ollama v0.32.7 adds Muse Glimmer 30B with DFlash and image input on Apple Silicon, plus streaming thinking traces and a `ctrl+o` trace toggle in the TUI. • Adds `muse-glimmer:30b-mlx` model tag, enabling the Muse Glimmer 30B multimodal model via `ollama run muse-glimmer:30b-mlx` or `ollama launch <integration> --model muse-glimmer:30b-mlx`. • Adds DFlash block-diffusion drafting support for the MLX engine on Apple Silicon, available with Muse Glimmer as of this release. • Adds image input support to the MLX engine (Muse Glimmer on Apple Silicon), enabling multimodal vision workloads locally. • Streams live thinking deltas beneath a `Thinking ↓ N tokens` row in the agent TUI, collapsing to a persistent `Thought` marker when the assistant begins responding. • Expands namespace tool declarations in the OpenAI Responses API, resolving undeclarable namespaced tool calls by unfolding nested `tools` arrays into namespace-qualified flat function names. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.6 https://github.com/ollama/ollama/releases/tag/v0.32.6 Tue, 04 Aug 2026 18:49:20 GMT Ollama v0.32.6 adds automatic MTP speculative decoding for Qwen3.5 on Apple GPUs and fixes OpenAI streaming wire format compliance • Adds `stream_options.include_usage` support in `/v1/chat/completions` so usage is returned in a separate trailing chunk, matching OpenAI's streaming wire format — `role` now appears only on the first chunk and `finish_reason` on its own chunk. • Qwen3.5 inference on Apple GPUs is faster: the MLX engine now automatically uses the model's MTP head for speculative decoding. • Experimental image generation has been removed; continue using v0.32.5 for image generation support. Breaking changes: • Experimental image generation is no longer available in v0.32.6; the feature has been removed and requires staying on v0.32.5. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.4 https://github.com/ollama/ollama/releases/tag/v0.32.4 Sat, 25 Jul 2026 02:22:12 GMT Ollama v0.32.4 adds Laguna MLX support with memory-resident models, agent skill permissions, and better speculative-decoding quantization. • Adds support for the Laguna model family on Apple Silicon via the MLX engine, with Metal memory residency for significantly improved prompt and generation performance on qualifying hardware. • Adds permission/approval flow for model-initiated agent skill loading, while preserving direct user slash-skill activation without prompts. • Adds `/system` prompt inspection and on/off toggle commands to the agent TUI, with cache-impact warnings and completion support. • Quantizes draft-model output heads at the requested quantization type when creating speculative-decoding drafts. • Supports per-expert quantization format decoding for Qwen3 MoE models, with a packed gate/up projection optimization yielding ~4–9% throughput improvement on M5 Max. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.3 https://github.com/ollama/ollama/releases/tag/v0.32.3 Thu, 23 Jul 2026 00:44:28 GMT Ollama v0.32.3 adds CUDA on Windows ARM64, B200/CUDA 12 support, Laguna 2.1 model capabilities, and lower iGPU memory use. • Adds CUDA support on Windows ARM64 devices. • Adds NVIDIA B200 GPU support via CUDA 12. • Reduces memory usage on Linux CUDA and ROCm integrated GPUs. • Adds chat, thinking, and tool calling support for Laguna 2.1 models. • Restores Claude Code Channels support when launching via `ollama launch claude`. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.1 https://github.com/ollama/ollama/releases/tag/v0.32.1 Thu, 16 Jul 2026 03:27:23 GMT Ollama v0.32.1 adds CWD-aware agent context, actionable web-auth guidance, and MLX load-timeout support. • Adds current working directory to the interactive agent's system prompt for better project context. • Agent web search and fetch now surface an actionable `ollama signin` prompt when authentication is required, instead of a generic error. • MLX text model loading now respects the `OLLAMA_LOAD_TIMEOUT` environment variable. • Improves Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.32.0 https://github.com/ollama/ollama/releases/tag/v0.32.0 Sat, 11 Jul 2026 01:03:46 GMT Ollama v0.32.0 adds an interactive agent TUI, renames the ChatGPT integration, and warns on deprecated agent models. • Adds an interactive agent experience: running `ollama` now launches a built-in agent for chat, coding, web search, and delegating real work. • Adds `--restore` flag to `ollama launch chatgpt` to return to your usual ChatGPT profile. • Simplifies the `ollama launch` root menu to a curated short list of popular integrations; all others remain accessible via `ollama launch <integration>`. • Warns before launching older/weaker agent models (CodeLlama, Qwen2.5, Qwen2.5-Coder, Llama 3.x, Mistral, StarCoder, base DeepSeek-R1 tags); use `--yes` to bypass in headless workflows. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.31.2 https://github.com/ollama/ollama/releases/tag/v0.31.2 Mon, 06 Jul 2026 22:28:22 GMT Ollama v0.31.2 adds flash attention on Pascal GPUs, iGPU vision-model offload, and privacy-hardened Claude Code launch. • Enables flash attention on older NVIDIA Pascal GPUs (compute capability 6.x), unlocking faster inference on GTX 10-series and similar cards. • Enables iGPU to offload vision models with padding to fit available memory, broadening multimodal support on integrated graphics. • Disables Claude Code telemetry, error reporting, feedback commands, and non-essential traffic by default when using `ollama launch claude`. • Updates the MLX and llama.cpp engines to their latest upstream versions. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.31.1 https://github.com/ollama/ollama/releases/tag/v0.31.1 Tue, 30 Jun 2026 22:10:17 GMT Gemma 4 on Apple Silicon gets ~90% faster token generation via automatic multi-token prediction (MTP), no config required. • Enables automatic multi-token prediction (MTP) for Gemma 4 on Apple Silicon, delivering ~90% faster token generation on coding-agent workloads with no configuration or output changes. • Adds minimum-version enforcement for `ollama launch hermes-desktop`, automatically upgrading older Hermes CLI installs (v0.16.0+ required) instead of failing silently. • Improves streamed tool-call parsing so closing braces or brackets inside JSON string argument values no longer cause tool calls to be silently dropped as plain text. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.11 https://github.com/ollama/ollama/releases/tag/v0.30.11 Thu, 25 Jun 2026 01:52:05 GMT Ollama v0.30.11 adds auto-install for Claude Code and OpenCode, thinking-capability detection, and improved Codex model-drift detection. • Adds auto-install for Claude Code: running `ollama launch claude` now prompts to install Claude Code automatically if the binary is missing. • Adds auto-install for OpenCode: running `ollama launch opencode` prompts to install OpenCode when it is not found, using the official install script on macOS/Linux and npm on Windows. • Adds thinking-capability detection for OpenCode: `ollama launch opencode` detects if the selected model supports reasoning and writes the appropriate config, enabling users to toggle thinking via Ctrl+T in OpenCode's TUI. • Adds model-drift detection for Codex App: `ollama launch codex-app` now detects when the Codex UI has switched to a non-Ollama model and marks the integration as inactive rather than silently mis-routing requests. • Adds sm_86 GPU architecture (RTX 30-series) to the CUDA v13 Windows preset, enabling CUDA acceleration on those GPUs under Windows. • Adds Compute Capability 87 (Jetson Orin) support for CUDA v13 on Jetson devices. • Enables the host Vulkan loader on Windows, broadening Vulkan backend compatibility. • Improves speculative decoding on the MLX runner with a unified, tuned decode path that maximizes throughput by dynamically choosing draft length. • Updates the bundled llama.cpp version, bringing in upstream model and performance improvements. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.10 https://github.com/ollama/ollama/releases/tag/v0.30.10 Wed, 17 Jun 2026 16:22:02 GMT Command A and North family models now run on Apple Silicon via the MLX engine; llama.cpp updated to b9672. • Adds MLX engine support for Cohere Command A and North family models (including North-Mini-Code) on Apple Silicon Macs. • Updates the llama.cpp backend to build b9672. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.9 https://github.com/ollama/ollama/releases/tag/v0.30.9 Mon, 15 Jun 2026 19:55:07 GMT Ollama v0.30.9 adds Cohere2Moe support and context-limit error reporting for oversized messages. • Adds support for the Cohere2Moe model architecture. • Returns an error when a single message exceeds the current context window size, preventing silent failures. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.8 https://github.com/ollama/ollama/releases/tag/v0.30.8 Fri, 12 Jun 2026 17:04:52 GMT Ollama v0.30.8 decouples prompt caching from context shift and adds a new `cache_prompt` API field for finer KV cache control. • Adds a new top-level `cache_prompt` field to generate and chat API requests, letting callers independently control KV cache reuse without affecting context-shift (`shift`) behavior. • Improves KV cache reuse by decoupling prompt caching from context shift, so `shift: false` no longer silently disables prompt caching. • Enhances MLX inference stability with hardened linear and embedding layers that guard against tensor over-promotion. • Adds prefill and speculative-decoding snapshot support to the MLX runner for more reliable multi-token prediction (MTP). • Improves recurrent model support by returning per-boundary states from gated-delta kernels. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.7 https://github.com/ollama/ollama/releases/tag/v0.30.7 Sun, 07 Jun 2026 21:51:48 GMT Ollama v0.30.7 adds Hermes Desktop launch support and aligns the OpenAI-compatible models list with available tags. • Adds `ollama launch hermes-desktop` to start a native desktop interface for the Hermes agent with conversation, integration, and messaging-app management. • Supports `HERMES_HOME` environment variable to override the Hermes config directory on any platform. • Uses the native Windows `%LOCALAPPDATA%\hermes` config path for Hermes Desktop, ensuring Ollama-written config is correctly picked up on Windows. • Aligns the OpenAI-compatible `/v1/models` endpoint model identifiers with those returned by `/api/tags`. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.6 https://github.com/ollama/ollama/releases/tag/v0.30.6 Fri, 05 Jun 2026 20:00:18 GMT Ollama v0.30.6 adds Oh My Pi (omp) coding-agent integration and QAT-optimized Gemma 4 model weights. • Adds `ollama launch omp` integration with Oh My Pi, an AI coding agent with IDE integration that runs in the terminal. • Adds Gemma 4 QAT model tags (`gemma4:*-qat`) with Quantization-Aware Training for dramatically reduced memory requirements on-device. • Enables NVFP4 global scale for MLX embedding layers on Apple Silicon, improving quantization quality for embedding workloads. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.5 https://github.com/ollama/ollama/releases/tag/v0.30.5 Thu, 04 Jun 2026 17:00:37 GMT Ollama v0.30.5 adds Hermes Desktop launch support and native Windows Hermes install via PowerShell. • Adds `ollama launch hermes-desktop` to launch the Hermes Desktop app, skipping rebuild when a packaged desktop app is already installed. • Enables `ollama launch hermes` on native Windows installs via the Hermes PowerShell installer. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.4 https://github.com/ollama/ollama/releases/tag/v0.30.4 Wed, 03 Jun 2026 18:48:32 GMT Ollama v0.30.4 adds Nemotron-3-Ultra, Metal GPU offload for multimodal models, and MLX REQUIRES support in Modelfiles. • Adds NVIDIA Nemotron-3-Ultra model, built for high-throughput reasoning and long-running agent workflows (`ollama run nemotron-3-ultra`). • Enables Metal GPU offload for multimodal (mmproj) models on Apple Silicon, accelerating vision/multimodal inference on supported Macs. • Supports `REQUIRES` directive in Modelfiles for MLX-based models when using `ollama create --experimental`. • Adds automatic migration for `ollama launch pi` users from the legacy `@mariozechner/pi-coding-agent` package to the official `@earendil-works/pi-coding-agent`, preserving npm install prefix. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.3 https://github.com/ollama/ollama/releases/tag/v0.30.3 Wed, 03 Jun 2026 16:35:43 GMT Ollama v0.30.3 adds support for Gemma 4 12B, Google's multimodal model optimized for laptop-class hardware. • Adds Gemma 4 12B model support — a multimodal model combining efficiency and advanced reasoning that runs on consumer laptops. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama https://github.com/ollama/ollama/releases/tag/v0.30.2 https://github.com/ollama/ollama/releases/tag/v0.30.2 Wed, 03 Jun 2026 00:37:18 GMT ollama launch adds Qwen Code + Cline CLI guidance, Laguna architecture support, and Radeon 8060S GPU enablement • Adds Qwen Code support to `ollama launch`, with guided Cline CLI installation when the CLI is missing. • Supports Poolside's Laguna model architecture in the llama.cpp backend. • Enables Radeon 8060S integrated GPUs by default. • Includes template details in logs to aid troubleshooting of model prompt formatting. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/ollama