Ollama

Track Ollama development. Run large language models locally.

About this developer podcast

Ollama turns GitHub activity into short audio updates.

Episodes cover commits, pull requests, issues, and release work.

Use this page to listen, subscribe, and find related developer podcasts.

This show page is the public hub for the podcast. It has one stable listen URL.

Use it to find RSS feeds, recent episodes, related shows, and older episode links.

If the project is quiet, new episodes may pause until there is useful activity to summarize.

Recent episodes from Ollama

  1. Gemma 4 Support and Platform Improvements

    Ollama's June 15th activity centers on comprehensive Gemma 4 model support with new MLX architecture implementations and memory optimizations, alongside critical fixes for multimodal processing and developer tooling improvements.

  2. Weekly Recap - MLX Performance & Path Handling

    This week brought major MLX cache optimizations and comprehensive fixes to file path handling across the CLI. The team also expanded hardware support with new backends and resolved critical GPU detection issues on hybrid systems.

  3. Memory Management and Multimodal Parsing Fixes

    A significant push to fix memory reporting bugs and improve file handling, with three memory-related fixes addressing double-counting issues and unified memory support, plus multimodal parsing improvements and new architecture support.

  4. GPU Offloading and Tool Call Fixes

    Today's activity centers on fixing GPU compatibility issues that were blocking hardware acceleration on integrated GPUs, plus resolving tool call parsing problems that affected AI agent functionality.

  5. Performance Optimizations and Model Handling Improvements

    Today's activity centers on performance optimizations and better model handling, with three merged fixes addressing launch provider drift, prompt caching separation, and tensor promotion issues, plus new capabilities for CPU-based…

  6. Infrastructure Updates and Platform Fixes

    Eight pull requests focused on critical infrastructure improvements, with llama.cpp updates resolving Windows crashes, GPU classification fixes for hybrid systems, and new gRPC integration alongside model support expansion.

  7. Multimodal Fixes and Developer Experience Updates

    Today's activity centers on fixing multimodal model capabilities detection and improving developer workflows. Six pull requests address audio-only model classification, MLX quantization validation, and VS Code integration enhancements.

  8. Cache Architecture Overhaul and Data Race Fixes

    Major cache improvements for MLX MTP speculation landed alongside critical fixes for data races in progress reporting and better error handling during model imports. The changes consolidate complex caching logic and improve reliability…

  9. Developer Tools and Cross-Platform Reliability
  10. Weekly Recap - Integration Expansion & Server Reliability
  11. Audio Support and Infrastructure Refinements
  12. Integration Ecosystem and API Consistency Push
  13. Platform Integration Expansion and API Reliability Fixes
  14. Model Integration and Windows System Improvements
  15. LLaMA Server Integration Hardening
  16. Integration Platform Expansion
  17. Model Integration Updates
  18. Weekly Recap - Infrastructure Modernization
  19. Major Architecture Overhaul Removes CGO Dependencies
  20. MLX Model Display Fixes and Template Parser Cleanup
  21. Weekly Recap - Performance Optimization & Launch System Improvements
  22. DFlash Speculative Decoding Rollback
  23. Model Inventory Refactoring
  24. Startup Performance Optimization
  25. Codex Integration Enhancement
  26. Weekly Recap - MLX Performance & Codex Integration
  27. Release Build Optimization
  28. Speculative Decoding and Codex App Updates
  29. MLX Sampler Overhaul and Codex Integration
  30. Vision Model Integration Enhancement
  31. MLX Threading and Claude Image Fixes
  32. Model Transfer Optimization and Test Reliability
  33. Claude Desktop Integration Removed
  34. Launch Command Enhancements
  35. Speed Revolution - MTP Decoding and Smart Caching
  36. Go 1.26 Runtime Update
  37. Weekly Recap - MLX Threading & Model Recommendations
  38. MLX Threading Fixes and Claude App Integration
  39. Model Recommendations and Windows Gateway Fix
  40. Metal GPU Stability and Gemma4 Updates
  41. Launch Experience Improvements and Model Recommendations
  42. Multi-Sequence Batching and New Model Support
  43. Tokenizer Bug Fix for BPE Processing
  44. Weekly Recap - MLX Performance & Launch Integrations
  45. MLX Sampling Performance Enhancement
  46. OpenAI Reasoning Integration
  47. Launch System Improvements and Integration Fixes
  48. Launch System Overhaul and Documentation Updates
  49. MLX Performance Boost and Model Updates
  50. New CLI Integration and Performance Improvements
  51. Weekly Recap - MLX Performance & Launch Integration Expansion
  52. MLX Sampler Improvements
  53. Windows WSL Integration Simplified
  54. Gemma4 Enhancements and Copilot CLI Integration
  55. Hermes Agent Integration and Gemma4 Improvements
  56. Gemma 4 MLX Support and Mixed-Precision Improvements
  57. Weekly Recap - Model Integration and Tooling Enhancements
  58. ROCm 7.2.1 Performance Update
  59. Gemma4 Parser Improvements
  60. Model Updates and Tool Call Fixes
  61. Error Handling and Modelfile Fixes
  62. Weekly Recap - Gemma4 Integration & Audio Support
  63. Performance Lessons and Gemma4 Refinements
  64. Gemma4 Arrives with Audio Magic
  65. Modernizing Codex Configuration
  66. Tokenizer Love and Better Model Support
  67. Legacy Compatibility and Developer Experience Wins
  68. Smoothing the Launch Experience
  69. Fixing the Inconsistencies That Matter
  70. Smart Caching and Better User Experience
  71. VS Code Integration Takes Center Stage
  72. Precision Revolution - New Float Formats and Testing Powerhouse
  73. MLX Performance Breakthrough and Smarter Caching
  74. Nvidia Partnership Takes Center Stage
  75. Bug Squashing Bonanza
  76. The Caching Revolution
  77. Bug Squashing and Launch Improvements
  78. Launch Command Gets a Major Polish
  79. Spring Cleaning and Performance Gains
  80. Thinking Streams and Local Tool Power-ups
  81. Stability First - Error Handling and Performance Fixes
  82. MLX Gets a Major Upgrade and Web Search Goes Live
  83. Simplifying the Sampling Story
  84. Cloud Models Get Smarter & Build Performance Boost
  85. Cloud Integrations Get Some Love
  86. Smarter Constraints and Qwen3.5 Boost
  87. Cloud Integration Drama and AI Model Expansion
  88. Smarter Sampling and Crash Prevention
  89. Building Bridges for Better Model Compatibility
  90. MLX Runner Gets Rock Solid
  91. Tool Calling Gets Smarter
  92. Cleaner Shutdowns and Faster Startups
  93. Qwen 3.5 Architecture Lands with Safety Upgrades
  94. Memory Management Revolution
  95. Nemotron Architecture Lands with Unified Cache Vision
  96. Fixing the WSL Plugin Problem
  97. Smarter UIs and Smoother Onboarding
  98. Tokenizer Consolidation & MLX Library Improvements
  99. Rolling Back and Rolling Forward
  100. Editor Integration Revolution

Episode archive for Ollama

  1. MLX Display Bug Squashing Day
  2. MLX Runner Gets Major Model Upgrades
  3. MLX Performance Breakthrough and Anthropic Search
  4. MLX Runner Revolution and Documentation Polish
  5. Refactoring Rollercoaster and Developer Experience Wins
  6. Bug Squashing Bonanza
  7. Smooth Onboarding for New Users
  8. Polish and Perfectionism - The Art of Getting the Details Right
  9. Cleaning Up the Config Game
  10. Speed Boost and Model Magic
  11. Memory Magic and Command Makeover
  12. Making Ollama Play Nice with Everyone
  13. The Great Cleanup - Manifests Get Their Own Home
  14. New Model Architecture and Image Generation Fixes
  15. New Model Support and Memory Management Wins
  16. FLUX.2 Image Generation Arrives
  17. Image Generation Goes Native and Parser Cleanup Magic
  18. Dynamic Loading and Experimental Models Take Center Stage
  19. Release Day Rescue Mission

More public developer podcasts

Browse other public Podlog show hubs with crawler-readable RSS and episode links.

  1. Agora Next Updates 155 episodes
  2. iCloud Photos Downloader 19 episodes
  3. Onlook Design Updates 21 episodes
  4. Buzz Transcription 51 episodes
  5. Frigate NVR Updates 132 episodes
  6. Ruby Core Updates 133 episodes
  7. Linux Kernel 119 episodes
  8. Homebrew 138 episodes
  9. TypeScript 53 episodes
  10. Ruby on Rails 131 episodes
  11. Redis 107 episodes
  12. Rust 110 episodes
  13. Python 123 episodes
  14. Go 126 episodes
  15. VS Code 141 episodes
  16. Node.js 135 episodes
  17. Django 127 episodes
  18. PostgreSQL 128 episodes
  19. Kubernetes 136 episodes
  20. Next.js 140 episodes
  21. Vue.js 87 episodes
  22. LangChain 121 episodes
  23. PyTorch 140 episodes
  24. Next.js Daily 142 episodes
  25. Navidrome Daily 4 episodes
  26. OpenAI Skills 52 episodes
  27. OpenClaw 99 episodes
  28. RuView 73 episodes
  29. Shannon 47 episodes
  30. Godot Daily 87 episodes
  31. Rails Daily 141 episodes
  32. Home Assistant Daily 146 episodes
  33. Linux Kernel Daily 124 episodes
  34. TailwindCSS 74 episodes
  35. AtomVM Daily 7 episodes
  36. Headroom Daily 1 episode
  37. Jabref Daily 3 episodes
  38. Jabref Daily 3 episodes
  39. Crush Daily 1 episode
  40. Agora Next Daily 1 episode
  41. React Native 125 episodes
  42. React Daily 79 episodes
  43. tiny-gpu Daily 15 episodes
  44. Pi Mono 63 episodes
  45. The Algorithm Daily 13 episodes