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. Cleaning Up the Agent Loop and Widening Model Support

    Ollama's team shipped new Laguna model support and an agent skills system, while trimming redundant work out of the TUI event loop and tightening streaming correctness for both OpenAI and Anthropic-compatible endpoints.

  2. Agent Package Gets a Major Consolidation

    A cluster of PRs from Parth Sareen reshaped the agent package's interface design, tool-round limits, and command surface, while separate fixes tightened streaming correctness and cache safety. The overall pattern is consolidation and…

  3. Agent Hardening and a Path Traversal Fix

    Parth Sareen led a cluster of agent and launch reliability fixes, while a separate security patch closes a path traversal risk in the fast download path for model layers. Together they mark a week focused on agent robustness and…

  4. Resource Leaks and GPU Placement Get a Clean-Up Pass

    A cluster of fixes targets goroutine and memory leaks across the GGUF parser, recurrent model caches, and background conversion jobs, while a separate group of changes corrects how Ollama places models across multiple GPUs. Both threads…

  5. Cleaning Up Memory Planning and the Launch Experience

    Ollama consolidated backend memory planning into one place and simplified the launch and integration surface, while several smaller fixes addressed chat template correctness, streaming behavior, and crash safety in model conversion. The…

  6. Fixing What Defaults Got Wrong

    Four pull requests landed today, and three of them share a common thread: correcting default settings and assumptions that quietly broke functionality, from image quality to malformed file handling to third-party tool behavior.

  7. Weekly Recap - Model Correctness and Runtime Hardening

    This week's work centered on fixing model-specific output bugs across Qwen, DeepSeek, and Gemma families, alongside a broad push to harden crash paths on Windows, macOS, and CUDA. Fifty pull request items and eleven additional commits…

  8. Tightening Up the Serving Layer

    Today's activity centers on server reliability and correctness — fixing a goroutine leak on client disconnect, correcting GPU device filtering on mixed hardware, and easing an outdated parallel-request restriction — alongside smaller API…

  9. Thinking Model Output Is Getting a Real Fix
  10. Stability Sweep Across Cloud, GPU, and Agent Tools
  11. Qwen3.5 Gets Untangled, and Small Bugs With Big Blast Radius
  12. Model Behavior Bugs and Blob Security Hardening
  13. Launch Gets Smarter, Model Support Gets Wider
  14. Cleaning Up the Scheduler's Edge Cases
  15. Weekly Recap - Rebuilding the Model Pipeline and Tightening the Guardrails
  16. Truth in Reporting
  17. MLX Create Pipeline Rewrite Lands
  18. Agent Harness Lands, Hardware Support Gets a Cleanup
  19. Gemma 4 Support and Platform Improvements
  20. Weekly Recap - MLX Performance & Path Handling
  21. Memory Management and Multimodal Parsing Fixes
  22. GPU Offloading and Tool Call Fixes
  23. Performance Optimizations and Model Handling Improvements
  24. Infrastructure Updates and Platform Fixes
  25. Multimodal Fixes and Developer Experience Updates
  26. Cache Architecture Overhaul and Data Race Fixes
  27. Developer Tools and Cross-Platform Reliability
  28. Weekly Recap - Integration Expansion & Server Reliability
  29. Audio Support and Infrastructure Refinements
  30. Integration Ecosystem and API Consistency Push
  31. Platform Integration Expansion and API Reliability Fixes
  32. Model Integration and Windows System Improvements
  33. LLaMA Server Integration Hardening
  34. Integration Platform Expansion
  35. Model Integration Updates
  36. Weekly Recap - Infrastructure Modernization
  37. Major Architecture Overhaul Removes CGO Dependencies
  38. MLX Model Display Fixes and Template Parser Cleanup
  39. Weekly Recap - Performance Optimization & Launch System Improvements
  40. DFlash Speculative Decoding Rollback
  41. Model Inventory Refactoring
  42. Startup Performance Optimization
  43. Codex Integration Enhancement
  44. Weekly Recap - MLX Performance & Codex Integration
  45. Release Build Optimization
  46. Speculative Decoding and Codex App Updates
  47. MLX Sampler Overhaul and Codex Integration
  48. Vision Model Integration Enhancement
  49. MLX Threading and Claude Image Fixes
  50. Model Transfer Optimization and Test Reliability
  51. Claude Desktop Integration Removed
  52. Launch Command Enhancements
  53. Speed Revolution - MTP Decoding and Smart Caching
  54. Go 1.26 Runtime Update
  55. Weekly Recap - MLX Threading & Model Recommendations
  56. MLX Threading Fixes and Claude App Integration
  57. Model Recommendations and Windows Gateway Fix
  58. Metal GPU Stability and Gemma4 Updates
  59. Launch Experience Improvements and Model Recommendations
  60. Multi-Sequence Batching and New Model Support
  61. Tokenizer Bug Fix for BPE Processing
  62. Weekly Recap - MLX Performance & Launch Integrations
  63. MLX Sampling Performance Enhancement
  64. OpenAI Reasoning Integration
  65. Launch System Improvements and Integration Fixes
  66. Launch System Overhaul and Documentation Updates
  67. MLX Performance Boost and Model Updates
  68. New CLI Integration and Performance Improvements
  69. Weekly Recap - MLX Performance & Launch Integration Expansion
  70. MLX Sampler Improvements
  71. Windows WSL Integration Simplified
  72. Gemma4 Enhancements and Copilot CLI Integration
  73. Hermes Agent Integration and Gemma4 Improvements
  74. Gemma 4 MLX Support and Mixed-Precision Improvements
  75. Weekly Recap - Model Integration and Tooling Enhancements
  76. ROCm 7.2.1 Performance Update
  77. Gemma4 Parser Improvements
  78. Model Updates and Tool Call Fixes
  79. Error Handling and Modelfile Fixes
  80. Weekly Recap - Gemma4 Integration & Audio Support
  81. Performance Lessons and Gemma4 Refinements
  82. Gemma4 Arrives with Audio Magic
  83. Modernizing Codex Configuration
  84. Tokenizer Love and Better Model Support
  85. Legacy Compatibility and Developer Experience Wins
  86. Smoothing the Launch Experience
  87. Fixing the Inconsistencies That Matter
  88. Smart Caching and Better User Experience
  89. VS Code Integration Takes Center Stage
  90. Precision Revolution - New Float Formats and Testing Powerhouse
  91. MLX Performance Breakthrough and Smarter Caching
  92. Nvidia Partnership Takes Center Stage
  93. Bug Squashing Bonanza
  94. The Caching Revolution
  95. Bug Squashing and Launch Improvements
  96. Launch Command Gets a Major Polish
  97. Spring Cleaning and Performance Gains
  98. Thinking Streams and Local Tool Power-ups
  99. Stability First - Error Handling and Performance Fixes
  100. MLX Gets a Major Upgrade and Web Search Goes Live

Episode archive for Ollama

  1. Simplifying the Sampling Story
  2. Cloud Models Get Smarter & Build Performance Boost
  3. Cloud Integrations Get Some Love
  4. Smarter Constraints and Qwen3.5 Boost
  5. Cloud Integration Drama and AI Model Expansion
  6. Smarter Sampling and Crash Prevention
  7. Building Bridges for Better Model Compatibility
  8. MLX Runner Gets Rock Solid
  9. Tool Calling Gets Smarter
  10. Cleaner Shutdowns and Faster Startups
  11. Qwen 3.5 Architecture Lands with Safety Upgrades
  12. Memory Management Revolution
  13. Nemotron Architecture Lands with Unified Cache Vision
  14. Fixing the WSL Plugin Problem
  15. Smarter UIs and Smoother Onboarding
  16. Tokenizer Consolidation & MLX Library Improvements
  17. Rolling Back and Rolling Forward
  18. Editor Integration Revolution
  19. MLX Display Bug Squashing Day
  20. MLX Runner Gets Major Model Upgrades
  21. MLX Performance Breakthrough and Anthropic Search
  22. MLX Runner Revolution and Documentation Polish
  23. Refactoring Rollercoaster and Developer Experience Wins
  24. Bug Squashing Bonanza
  25. Smooth Onboarding for New Users
  26. Polish and Perfectionism - The Art of Getting the Details Right
  27. Cleaning Up the Config Game
  28. Speed Boost and Model Magic
  29. Memory Magic and Command Makeover
  30. Making Ollama Play Nice with Everyone
  31. The Great Cleanup - Manifests Get Their Own Home
  32. New Model Architecture and Image Generation Fixes
  33. New Model Support and Memory Management Wins
  34. FLUX.2 Image Generation Arrives
  35. Image Generation Goes Native and Parser Cleanup Magic
  36. Dynamic Loading and Experimental Models Take Center Stage
  37. Release Day Rescue Mission

More public developer podcasts

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

  1. Next Js Daily 8 episodes
  2. Headroom Daily 17 episodes
  3. Agent Of Empires Daily 9 episodes
  4. Frigate NVR Updates 148 episodes
  5. Linux Kernel 135 episodes
  6. Homebrew 156 episodes
  7. TypeScript 62 episodes
  8. Ruby on Rails 149 episodes
  9. Redis 125 episodes
  10. Next.js 158 episodes
  11. Vue.js 102 episodes
  12. Rust 128 episodes
  13. Ruby Core Updates 151 episodes
  14. Python 141 episodes
  15. Go 142 episodes
  16. VS Code 159 episodes
  17. TailwindCSS 89 episodes
  18. Node.js 153 episodes
  19. Django 145 episodes
  20. PostgreSQL 146 episodes
  21. Kubernetes 154 episodes
  22. LangChain 139 episodes
  23. PyTorch 158 episodes
  24. Maestro Daily 7 episodes
  25. Videorc Daily 11 episodes
  26. Navidrome Daily 22 episodes
  27. Next.js Daily 160 episodes
  28. OpenClaw 117 episodes
  29. RuView 86 episodes
  30. Godot Daily 105 episodes
  31. Agora Next Updates 175 episodes
  32. Rails Daily 159 episodes
  33. Linux Kernel Daily 140 episodes
  34. Home Assistant Daily 164 episodes
  35. BlocksBeyondTheStars Daily 6 episodes
  36. Jabref Daily 19 episodes
  37. Jabref Daily 19 episodes
  38. Buzz Transcription 55 episodes
  39. Shannon 55 episodes
  40. Agora Next Daily 7 episodes
  41. Onlook Design Updates 26 episodes
  42. iCloud Photos Downloader 21 episodes
  43. tiny-gpu Daily 18 episodes
  44. NativeScript iOS Daily 4 episodes
  45. AtomVM Daily 8 episodes
  46. OpenAI Skills 52 episodes
  47. Crush Daily 1 episode
  48. React Native 125 episodes
  49. React Daily 79 episodes
  50. Pi Mono 63 episodes
  51. The Algorithm Daily 13 episodes
  52. ControlNet Daily 0 episodes
  53. FinceptTerminal Daily 0 episodes