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. Runner Reliability and a Documentation Cleanup Wave

    The MLX runner picked up context-length enforcement and repeat-loop protection to match the llama.cpp backend's behavior, while a separate contributor pushed through nine documentation fixes in a single morning. Together they show a…

  2. Proxy Fix and a Documentation Cleanup Sweep

    A single security-relevant fix closes a proxy gap in Ollama's file transfer path, while four separate documentation pull requests tidy up grammar and formatting in the README and API docs.

  3. Weekly Recap - Claude Desktop Integration & MLX Engine Maturity

    This week's work centered on two fronts: a major push to make Claude Desktop a first-class integration across macOS and Windows, and a series of correctness fixes hardening the MLX engine for structured output, model loading, and Windows…

  4. Correctness Fixes Under the Hood

    Today's activity centers on quiet correctness fixes — a GGUF parsing bug that silently corrupted tensor alignment, a Vulkan regression that broke model loading on integrated GPUs, and stricter but more forgiving API schema handling —…

  5. Agent Expansion, Desktop Polish, and a Documentation Sweep

    Ollama's agent and desktop surfaces both grew today, with new environment-aware tooling and Windows Claude Desktop support landing alongside a performance fix for structured output on the MLX runner. A separate wave of small…

  6. MLX Engine Grows Up

    The MLX engine picked up multimodal support and quantization safeguards this cycle, while a cluster of small documentation fixes and a quantization validation guard rounded out a quieter maintenance day.

  7. Desktop App Stability and the Claude Integration Cleanup

    The desktop app got a coordinated overhaul of process handoff, sign-in state, and Claude Desktop integration, while the model runtime side saw fixes for MLX error handling and a long-standing CUDA decoding bug in Qwen 2.5 VL.

  8. MLX Runner Hardens Up, Claude Desktop Gets Real Estate

    The MLX runner picked up structured output and a fix for GPU timeouts on slow storage, while a cluster of security-minded fixes closed off SSRF and CORS gaps across the app and downloader. Meanwhile, Claude Desktop integration continued…

  9. Claude Desktop Integration Overhaul
  10. Hardening the Runner Scheduler
  11. Weekly Recap - Desktop Apps Grow Up, Inference Gets More Reliable
  12. Visibility Into What the Model Actually Sees
  13. Fixing the Long-Prompt Timeout Trap
  14. Claude Desktop Gets Deep App Integration
  15. Closing the Gaps on Hung Requests and Broken Installs
  16. Closing the Gap on Model Metadata Overhead
  17. Silent Failures Get Loud
  18. Fixing the Small Gaps Between Local and Cloud
  19. Weekly Recap - Model Compatibility and the Push Into Coding Agents
  20. Silent Failures Get Louder
  21. Qwen Gets Serious About Coding Agents
  22. Launch Ecosystem Expands, Parser Edge Cases Get Squashed
  23. Backup Collisions and a Security Fix Converge
  24. Fixing the Defaults That Silently Hurt You
  25. Model Coverage and Tool-Call Reliability
  26. Vision Support Lands in the MLX Runner
  27. Weekly Recap - Vision Runners and Robustness Cleanup
  28. Edge Case Cleanup Across the Stack
  29. Speculative Decoding Gets a New Draft Architecture
  30. Crash Fixes and the Launcher Ecosystem Grows
  31. Silent Data Corruption Fixes
  32. Hardening the Thinking and Tool-Call Pipeline
  33. Closing the Gaps Where Failures Go Silent
  34. Streams That Fail Silently, Fixed
  35. Weekly Recap - Speed, Speculation, and Scheduler Reliability
  36. Scheduler Reliability Overhaul
  37. Speculative Decoding and the Cloud Model Nudge
  38. API Compatibility and Model Correctness Push
  39. Speculative Decoding Gains and a Lint Lockdown
  40. Cleaning Up Concurrency and Cutting Experimental Code
  41. Trust Your Cache, Fix Your Logs
  42. Parsing Bugs and Process Hardening
  43. Weekly Recap - New Model Support & Concurrency Hardening
  44. Closing the Gaps Between Local Config and Cloud Compatibility
  45. MLX Performance Push and a Scheduler Race Fix
  46. A Server Reliability Sweep
  47. Tool Calling Gets a Reliability Pass
  48. Scheduler Race Conditions Take Center Stage
  49. Command Line Consolidation and Hardware Fixes
  50. Thinking Models Leak Control Tokens
  51. Weekly Recap - Hardening the Runtime, One Edge Case at a Time
  52. Closing the Gaps Between API Layers
  53. Cleaning Up the Agent Loop and Widening Model Support
  54. Agent Package Gets a Major Consolidation
  55. Agent Hardening and a Path Traversal Fix
  56. Resource Leaks and GPU Placement Get a Clean-Up Pass
  57. Cleaning Up Memory Planning and the Launch Experience
  58. Fixing What Defaults Got Wrong
  59. Weekly Recap - Model Correctness and Runtime Hardening
  60. Tightening Up the Serving Layer
  61. Thinking Model Output Is Getting a Real Fix
  62. Stability Sweep Across Cloud, GPU, and Agent Tools
  63. Qwen3.5 Gets Untangled, and Small Bugs With Big Blast Radius
  64. Model Behavior Bugs and Blob Security Hardening
  65. Launch Gets Smarter, Model Support Gets Wider
  66. Cleaning Up the Scheduler's Edge Cases
  67. Weekly Recap - Rebuilding the Model Pipeline and Tightening the Guardrails
  68. Truth in Reporting
  69. MLX Create Pipeline Rewrite Lands
  70. Agent Harness Lands, Hardware Support Gets a Cleanup
  71. Gemma 4 Support and Platform Improvements
  72. Weekly Recap - MLX Performance & Path Handling
  73. Memory Management and Multimodal Parsing Fixes
  74. GPU Offloading and Tool Call Fixes
  75. Performance Optimizations and Model Handling Improvements
  76. Infrastructure Updates and Platform Fixes
  77. Multimodal Fixes and Developer Experience Updates
  78. Cache Architecture Overhaul and Data Race Fixes
  79. Developer Tools and Cross-Platform Reliability
  80. Weekly Recap - Integration Expansion & Server Reliability
  81. Audio Support and Infrastructure Refinements
  82. Integration Ecosystem and API Consistency Push
  83. Platform Integration Expansion and API Reliability Fixes
  84. Model Integration and Windows System Improvements
  85. LLaMA Server Integration Hardening
  86. Integration Platform Expansion
  87. Model Integration Updates
  88. Weekly Recap - Infrastructure Modernization
  89. Major Architecture Overhaul Removes CGO Dependencies
  90. MLX Model Display Fixes and Template Parser Cleanup
  91. Weekly Recap - Performance Optimization & Launch System Improvements
  92. DFlash Speculative Decoding Rollback
  93. Model Inventory Refactoring
  94. Startup Performance Optimization
  95. Codex Integration Enhancement
  96. Weekly Recap - MLX Performance & Codex Integration
  97. Release Build Optimization
  98. Speculative Decoding and Codex App Updates
  99. MLX Sampler Overhaul and Codex Integration
  100. Vision Model Integration Enhancement

Episode archive for Ollama

  1. MLX Threading and Claude Image Fixes
  2. Model Transfer Optimization and Test Reliability
  3. Claude Desktop Integration Removed
  4. Launch Command Enhancements
  5. Speed Revolution - MTP Decoding and Smart Caching
  6. Go 1.26 Runtime Update
  7. Weekly Recap - MLX Threading & Model Recommendations
  8. MLX Threading Fixes and Claude App Integration
  9. Model Recommendations and Windows Gateway Fix
  10. Metal GPU Stability and Gemma4 Updates
  11. Launch Experience Improvements and Model Recommendations
  12. Multi-Sequence Batching and New Model Support
  13. Tokenizer Bug Fix for BPE Processing
  14. Weekly Recap - MLX Performance & Launch Integrations
  15. MLX Sampling Performance Enhancement
  16. OpenAI Reasoning Integration
  17. Launch System Improvements and Integration Fixes
  18. Launch System Overhaul and Documentation Updates
  19. MLX Performance Boost and Model Updates
  20. New CLI Integration and Performance Improvements
  21. Weekly Recap - MLX Performance & Launch Integration Expansion
  22. MLX Sampler Improvements
  23. Windows WSL Integration Simplified
  24. Gemma4 Enhancements and Copilot CLI Integration
  25. Hermes Agent Integration and Gemma4 Improvements
  26. Gemma 4 MLX Support and Mixed-Precision Improvements
  27. Weekly Recap - Model Integration and Tooling Enhancements
  28. ROCm 7.2.1 Performance Update
  29. Gemma4 Parser Improvements
  30. Model Updates and Tool Call Fixes
  31. Error Handling and Modelfile Fixes
  32. Weekly Recap - Gemma4 Integration & Audio Support
  33. Performance Lessons and Gemma4 Refinements
  34. Gemma4 Arrives with Audio Magic
  35. Modernizing Codex Configuration
  36. Tokenizer Love and Better Model Support
  37. Legacy Compatibility and Developer Experience Wins
  38. Smoothing the Launch Experience
  39. Fixing the Inconsistencies That Matter
  40. Smart Caching and Better User Experience
  41. VS Code Integration Takes Center Stage
  42. Precision Revolution - New Float Formats and Testing Powerhouse
  43. MLX Performance Breakthrough and Smarter Caching
  44. Nvidia Partnership Takes Center Stage
  45. Bug Squashing Bonanza
  46. The Caching Revolution
  47. Bug Squashing and Launch Improvements
  48. Launch Command Gets a Major Polish
  49. Spring Cleaning and Performance Gains
  50. Thinking Streams and Local Tool Power-ups
  51. Stability First - Error Handling and Performance Fixes
  52. MLX Gets a Major Upgrade and Web Search Goes Live
  53. Simplifying the Sampling Story
  54. Cloud Models Get Smarter & Build Performance Boost
  55. Cloud Integrations Get Some Love
  56. Smarter Constraints and Qwen3.5 Boost
  57. Cloud Integration Drama and AI Model Expansion
  58. Smarter Sampling and Crash Prevention
  59. Building Bridges for Better Model Compatibility
  60. MLX Runner Gets Rock Solid
  61. Tool Calling Gets Smarter
  62. Cleaner Shutdowns and Faster Startups
  63. Qwen 3.5 Architecture Lands with Safety Upgrades
  64. Memory Management Revolution
  65. Nemotron Architecture Lands with Unified Cache Vision
  66. Fixing the WSL Plugin Problem
  67. Smarter UIs and Smoother Onboarding
  68. Tokenizer Consolidation & MLX Library Improvements
  69. Rolling Back and Rolling Forward
  70. Editor Integration Revolution
  71. MLX Display Bug Squashing Day
  72. MLX Runner Gets Major Model Upgrades
  73. MLX Performance Breakthrough and Anthropic Search
  74. MLX Runner Revolution and Documentation Polish
  75. Refactoring Rollercoaster and Developer Experience Wins
  76. Bug Squashing Bonanza
  77. Smooth Onboarding for New Users
  78. Polish and Perfectionism - The Art of Getting the Details Right
  79. Cleaning Up the Config Game
  80. Speed Boost and Model Magic
  81. Memory Magic and Command Makeover
  82. Making Ollama Play Nice with Everyone
  83. The Great Cleanup - Manifests Get Their Own Home
  84. New Model Architecture and Image Generation Fixes
  85. New Model Support and Memory Management Wins
  86. FLUX.2 Image Generation Arrives
  87. Image Generation Goes Native and Parser Cleanup Magic
  88. Dynamic Loading and Experimental Models Take Center Stage
  89. 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 213 episodes
  2. Pi Mono 93 episodes
  3. OpenClaw 170 episodes
  4. RuView 131 episodes
  5. Godot Daily 158 episodes
  6. Agora Next Updates 228 episodes
  7. Rails Daily 212 episodes
  8. Home Assistant Daily 217 episodes
  9. Linux Kernel Daily 193 episodes
  10. React Daily 109 episodes
  11. Jabref Daily 64 episodes
  12. BlocksBeyondTheStars Daily 46 episodes
  13. Jabref Daily 65 episodes
  14. Next Js Daily 53 episodes
  15. Headroom Daily 62 episodes
  16. Agent Of Empires Daily 53 episodes
  17. Frigate NVR Updates 196 episodes
  18. Linux Kernel 187 episodes
  19. Homebrew 208 episodes
  20. TypeScript 97 episodes
  21. Ruby on Rails 201 episodes
  22. Redis 176 episodes
  23. Next.js 210 episodes
  24. Vue.js 149 episodes
  25. Rust 180 episodes
  26. Ruby Core Updates 203 episodes
  27. Python 193 episodes
  28. Go 193 episodes
  29. VS Code 211 episodes
  30. Node.js 205 episodes
  31. Django 197 episodes
  32. React Native 154 episodes
  33. PostgreSQL 197 episodes
  34. Kubernetes 206 episodes
  35. LangChain 191 episodes
  36. PyTorch 210 episodes
  37. Openharness Daily 25 episodes
  38. Maestro Daily 52 episodes
  39. Videorc Daily 53 episodes
  40. Navidrome Daily 71 episodes
  41. Shannon 83 episodes
  42. iCloud Photos Downloader 27 episodes
  43. Onlook Design Updates 34 episodes
  44. Buzz Transcription 80 episodes
  45. The Algorithm Daily 15 episodes
  46. TailwindCSS 119 episodes
  47. AtomVM Daily 15 episodes
  48. NativeScript iOS Daily 26 episodes
  49. Agora Next Daily 12 episodes
  50. Energy Inc Ace Mate Learning Daily 2 episodes
  51. tiny-gpu Daily 20 episodes
  52. OpenAI Skills 52 episodes
  53. Crush Daily 1 episode
  54. ControlNet Daily 0 episodes
  55. FinceptTerminal Daily 0 episodes