Ollama 0.40.13 expands LFM3 support beyond Apple Silicon
Updated Ollama
Summary
The release adds Linux and Windows support for LFM3 and speech output for its audio variants.
- Tool
- Ollama
- Category
- Agent infra
- Date
- Pricing
- Not stated in the sources we cited.
Ollama 0.40.13 expands the supported platforms for LFM3. The release notes list Linux and Windows in addition to Apple Silicon.
It also adds text-to-speech support for lfm3-audio and lfm3-omni. These are model-specific capabilities, not a claim that every model served through Ollama can generate speech.
For someone evaluating a local LFM3 workflow, the useful change is the broader platform coverage and audio-output support. The short release note does not establish minimum hardware, throughput, output quality or model-license terms. Check the linked model pages before choosing hardware or a commercial deployment; local execution should not be confused with a hosted free tier.
See the ollama hub.
More from Ollama
Ollama 0.40.11 adds macOS speech and d3 decisions
OllamaOllama adds streamed speech generation on macOS and d3 models for classification and probability-based decisions.
Category: Agent infra
Pricing: Not stated
Ollama 0.40.7-rc0 adds PPLX Decider support in MLX
OllamaA prerelease adds PPLX Decider v1.2 support and adjusts Responses compatibility and speculative-draft handling.
Category: Agent infra
Pricing: Open source
Ollama 0.40.6 adds Clef cloud support and q2_0 types
OllamaOllama’s October 16 release adds Clef in its cloud service, GGUF q2_0 types and a Windows runner cleanup fix.
Category: Agent infra
Pricing: Open source
Ollama 0.40.2 upgrades downloaded models for llama.cpp
OllamaOllama v0.40.2, released October 8, 2026, upgrades previously downloaded models in the background for llama.cpp and keeps backups for safe downgrades.
Category: Coding agents
Pricing: Open source
Questions
What is Ollama?
According to its site, Ollama gives access to the latest open models with privacy, locally or in the cloud. The repository describes it as a way to get up and running with models such as Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen and Gemma.
Is Ollama open source?
The GitHub API reports the ollama/ollama repository license as MIT.
What is the latest launch tracked here?
Ollama v0.40.2, published October 8, 2026, which upgrades previously downloaded models in the background for llama.cpp.
Filed on Agent Radar. Claims in this note are limited to the sources above.