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. Proxy Transfers and API Resilience

    Merged fixes harden registry downloads behind proxies and make the Responses API tolerant when switching to non-thinking models. Open proposals target raw output tokens, large-number precision, and model lookup races, alongside cloud…

  2. Model Compatibility Catch-Up and Windows Reliability

    Ollama's runtime caught up to new model formats with a llama.cpp bump, Q2_0 support, and Nemotron MLX fixes, alongside a Windows fix for orphaned runners and agent prompt corrections. Docs and community listings made up the rest of the…

  3. Responses Compatibility and Clearer Errors

    Most activity centers on making the Responses API and ChatGPT gateway tolerate real-world history and report auth and payment failures clearly. Supporting fixes address tool-call parsing, model runtimes, and proxy correctness.

  4. Decision Models Go Usable, MLX Speeds Up on CUDA

    Decision models became runnable from the command line with corrected scoring and new integration tests, while the MLX backend gained CUDA kernel ports and faster Gemma 4 prefill. Cloud billing saw stopgap fixes for usage credits and…

  5. Decision Scoring Matures as Inference Hardens

    Decision-model work dominated with Kev support on MLX and consistency fixes, while core inference gained manifest reuse and memory and compatibility fixes. Docs restructuring was merged, reverted, and re-proposed alongside smaller…

  6. Native Decision Models and Precision Fixes

    Ollama shifted decision-model scoring into upstream llama.cpp and added multimodal embedding support, while fixing tool-call precision and model loading reliability. The pattern is less custom code, fewer edge-case failures.

  7. Weekly Recap - Decision Models Go Native, Embeddings Go Multimodal

    Ollama shifted decision-model scoring into upstream llama.cpp and added multimodal embeddings, alongside fixes for OpenAI compatibility and Windows model storage. The pattern this week is retiring custom patches in favor of native runner…

  8. GPU Discovery Fallback and Docs Cleanup

    Twelve pull requests were dominated by ten low-risk docs fixes, with the functional impact concentrated in PR #18923 adding a native-probe fallback for empty GPU discovery output, plus a sidebar load-animation fix in PR #18937.

  9. OpenAI Parity and Reasoning Fixes
  10. Legacy Model Cleanup and Agent Launcher Polish
  11. Memory Accuracy, Tool Fixes, and Simpler Onboarding
  12. Multimodal Embeddings and Cloud Convergence
  13. MLX Performance Push and Tool-Call Reliability
  14. Tokenizer Parity and RC-Aware Updates
  15. Weekly Recap - System One Decisions Take Center Stage
  16. MLX Tokenizer Fixes and Thinking Model Reliability
  17. Tool Call Ordering Fixes and Decision Models
  18. Decision Models Take Shape
  19. Pointer-Head Scoring and Reliability Fixes
  20. System One Moves to Explicit Capabilities
  21. System One Decisions Launch
  22. Silent Sampling Overrides Fixed
  23. Weekly Recap - Single-Pass Structured Outputs and MLX Speedups
  24. Tool-Call Reliability Fixes
  25. Desktop Fixes and API Correctness
  26. Mac Polish, MLX Reliability, and Compatibility Fixes
  27. GPU Efficiency Fix and MLX Hardening
  28. Single-Pass Structured Outputs and MLX Speedups
  29. Agent Reliability Fixes and Offline Model Transfer
  30. Thinking Separation Fix and GPU Visibility
  31. Weekly Recap - MLX Graduation, Reasoning Fixes, and Onboarding Polish
  32. Compatibility Fixes and Mac Efficiency
  33. Closing the Gaps Between Model Metadata and Client Compatibility
  34. Hardening Pass Across Network, Memory, and Release Paths
  35. The MLX Engine Comes Home
  36. Streaming Reliability and Parser Cleanup
  37. MLX Comes of Age, Cancellation Gets Fixed
  38. Consistency Fixes for Tool Schemas and Image Input
  39. Weekly Recap - Memory Discipline and Tool-Calling Cleanup
  40. Precision Fixes and Cleanup
  41. Silent Failures Get Loud
  42. Taming Memory in the MLX Runner
  43. Tool-Call Parsing Gets a Hardening Pass
  44. Codex Integration Hardening and Streaming Reliability
  45. Tightening Up the OpenAI Compatibility Layer
  46. Closing the Gaps Between What You Configure and What Actually Runs
  47. Weekly Recap - MLX Hardens as a First-Class Engine
  48. Context Handling Gets Serious
  49. Codex Integration Push and Schema Hardening
  50. Structured Output Meets Speculative Decoding
  51. Hardening the MLX Engine and Fixing What Feeds the Scheduler
  52. MLX Grows Up, Model Intent Gets Respected
  53. Runner Reliability and a Documentation Cleanup Wave
  54. Proxy Fix and a Documentation Cleanup Sweep
  55. Weekly Recap - Claude Desktop Integration & MLX Engine Maturity
  56. Correctness Fixes Under the Hood
  57. Agent Expansion, Desktop Polish, and a Documentation Sweep
  58. MLX Engine Grows Up
  59. Desktop App Stability and the Claude Integration Cleanup
  60. MLX Runner Hardens Up, Claude Desktop Gets Real Estate
  61. Claude Desktop Integration Overhaul
  62. Hardening the Runner Scheduler
  63. Weekly Recap - Desktop Apps Grow Up, Inference Gets More Reliable
  64. Visibility Into What the Model Actually Sees
  65. Fixing the Long-Prompt Timeout Trap
  66. Claude Desktop Gets Deep App Integration
  67. Closing the Gaps on Hung Requests and Broken Installs
  68. Closing the Gap on Model Metadata Overhead
  69. Silent Failures Get Loud
  70. Fixing the Small Gaps Between Local and Cloud
  71. Weekly Recap - Model Compatibility and the Push Into Coding Agents
  72. Silent Failures Get Louder
  73. Qwen Gets Serious About Coding Agents
  74. Launch Ecosystem Expands, Parser Edge Cases Get Squashed
  75. Backup Collisions and a Security Fix Converge
  76. Fixing the Defaults That Silently Hurt You
  77. Model Coverage and Tool-Call Reliability
  78. Vision Support Lands in the MLX Runner
  79. Weekly Recap - Vision Runners and Robustness Cleanup
  80. Edge Case Cleanup Across the Stack
  81. Speculative Decoding Gets a New Draft Architecture
  82. Crash Fixes and the Launcher Ecosystem Grows
  83. Silent Data Corruption Fixes
  84. Hardening the Thinking and Tool-Call Pipeline
  85. Closing the Gaps Where Failures Go Silent
  86. Streams That Fail Silently, Fixed
  87. Weekly Recap - Speed, Speculation, and Scheduler Reliability
  88. Scheduler Reliability Overhaul
  89. Speculative Decoding and the Cloud Model Nudge
  90. API Compatibility and Model Correctness Push
  91. Speculative Decoding Gains and a Lint Lockdown
  92. Cleaning Up Concurrency and Cutting Experimental Code
  93. Trust Your Cache, Fix Your Logs
  94. Parsing Bugs and Process Hardening
  95. Weekly Recap - New Model Support & Concurrency Hardening
  96. Closing the Gaps Between Local Config and Cloud Compatibility
  97. MLX Performance Push and a Scheduler Race Fix
  98. A Server Reliability Sweep
  99. Tool Calling Gets a Reliability Pass
  100. Scheduler Race Conditions Take Center Stage

Episode archive for Ollama

  1. Command Line Consolidation and Hardware Fixes
  2. Thinking Models Leak Control Tokens
  3. Weekly Recap - Hardening the Runtime, One Edge Case at a Time
  4. Closing the Gaps Between API Layers
  5. Cleaning Up the Agent Loop and Widening Model Support
  6. Agent Package Gets a Major Consolidation
  7. Agent Hardening and a Path Traversal Fix
  8. Resource Leaks and GPU Placement Get a Clean-Up Pass
  9. Cleaning Up Memory Planning and the Launch Experience
  10. Fixing What Defaults Got Wrong
  11. Weekly Recap - Model Correctness and Runtime Hardening
  12. Tightening Up the Serving Layer
  13. Thinking Model Output Is Getting a Real Fix
  14. Stability Sweep Across Cloud, GPU, and Agent Tools
  15. Qwen3.5 Gets Untangled, and Small Bugs With Big Blast Radius
  16. Model Behavior Bugs and Blob Security Hardening
  17. Launch Gets Smarter, Model Support Gets Wider
  18. Cleaning Up the Scheduler's Edge Cases
  19. Weekly Recap - Rebuilding the Model Pipeline and Tightening the Guardrails
  20. Truth in Reporting
  21. MLX Create Pipeline Rewrite Lands
  22. Agent Harness Lands, Hardware Support Gets a Cleanup
  23. Gemma 4 Support and Platform Improvements
  24. Weekly Recap - MLX Performance & Path Handling
  25. Memory Management and Multimodal Parsing Fixes
  26. GPU Offloading and Tool Call Fixes
  27. Performance Optimizations and Model Handling Improvements
  28. Infrastructure Updates and Platform Fixes
  29. Multimodal Fixes and Developer Experience Updates
  30. Cache Architecture Overhaul and Data Race Fixes
  31. Developer Tools and Cross-Platform Reliability
  32. Weekly Recap - Integration Expansion & Server Reliability
  33. Audio Support and Infrastructure Refinements
  34. Integration Ecosystem and API Consistency Push
  35. Platform Integration Expansion and API Reliability Fixes
  36. Model Integration and Windows System Improvements
  37. LLaMA Server Integration Hardening
  38. Integration Platform Expansion
  39. Model Integration Updates
  40. Weekly Recap - Infrastructure Modernization
  41. Major Architecture Overhaul Removes CGO Dependencies
  42. MLX Model Display Fixes and Template Parser Cleanup
  43. Weekly Recap - Performance Optimization & Launch System Improvements
  44. DFlash Speculative Decoding Rollback
  45. Model Inventory Refactoring
  46. Startup Performance Optimization
  47. Codex Integration Enhancement
  48. Weekly Recap - MLX Performance & Codex Integration
  49. Release Build Optimization
  50. Speculative Decoding and Codex App Updates
  51. MLX Sampler Overhaul and Codex Integration
  52. Vision Model Integration Enhancement
  53. MLX Threading and Claude Image Fixes
  54. Model Transfer Optimization and Test Reliability
  55. Claude Desktop Integration Removed
  56. Launch Command Enhancements
  57. Speed Revolution - MTP Decoding and Smart Caching
  58. Go 1.26 Runtime Update
  59. Weekly Recap - MLX Threading & Model Recommendations
  60. MLX Threading Fixes and Claude App Integration
  61. Model Recommendations and Windows Gateway Fix
  62. Metal GPU Stability and Gemma4 Updates
  63. Launch Experience Improvements and Model Recommendations
  64. Multi-Sequence Batching and New Model Support
  65. Tokenizer Bug Fix for BPE Processing
  66. Weekly Recap - MLX Performance & Launch Integrations
  67. MLX Sampling Performance Enhancement
  68. OpenAI Reasoning Integration
  69. Launch System Improvements and Integration Fixes
  70. Launch System Overhaul and Documentation Updates
  71. MLX Performance Boost and Model Updates
  72. New CLI Integration and Performance Improvements
  73. Weekly Recap - MLX Performance & Launch Integration Expansion
  74. MLX Sampler Improvements
  75. Windows WSL Integration Simplified
  76. Gemma4 Enhancements and Copilot CLI Integration
  77. Hermes Agent Integration and Gemma4 Improvements
  78. Gemma 4 MLX Support and Mixed-Precision Improvements
  79. Weekly Recap - Model Integration and Tooling Enhancements
  80. ROCm 7.2.1 Performance Update
  81. Gemma4 Parser Improvements
  82. Model Updates and Tool Call Fixes
  83. Error Handling and Modelfile Fixes
  84. Weekly Recap - Gemma4 Integration & Audio Support
  85. Performance Lessons and Gemma4 Refinements
  86. Gemma4 Arrives with Audio Magic
  87. Modernizing Codex Configuration
  88. Tokenizer Love and Better Model Support
  89. Legacy Compatibility and Developer Experience Wins
  90. Smoothing the Launch Experience
  91. Fixing the Inconsistencies That Matter
  92. Smart Caching and Better User Experience
  93. VS Code Integration Takes Center Stage
  94. Precision Revolution - New Float Formats and Testing Powerhouse
  95. MLX Performance Breakthrough and Smarter Caching
  96. Nvidia Partnership Takes Center Stage
  97. Bug Squashing Bonanza
  98. The Caching Revolution
  99. Bug Squashing and Launch Improvements
  100. Launch Command Gets a Major Polish
  101. Spring Cleaning and Performance Gains
  102. Thinking Streams and Local Tool Power-ups
  103. Stability First - Error Handling and Performance Fixes
  104. MLX Gets a Major Upgrade and Web Search Goes Live
  105. Simplifying the Sampling Story
  106. Cloud Models Get Smarter & Build Performance Boost
  107. Cloud Integrations Get Some Love
  108. Smarter Constraints and Qwen3.5 Boost
  109. Cloud Integration Drama and AI Model Expansion
  110. Smarter Sampling and Crash Prevention
  111. Building Bridges for Better Model Compatibility
  112. MLX Runner Gets Rock Solid
  113. Tool Calling Gets Smarter
  114. Cleaner Shutdowns and Faster Startups
  115. Qwen 3.5 Architecture Lands with Safety Upgrades
  116. Memory Management Revolution
  117. Nemotron Architecture Lands with Unified Cache Vision
  118. Fixing the WSL Plugin Problem
  119. Smarter UIs and Smoother Onboarding
  120. Tokenizer Consolidation & MLX Library Improvements
  121. Rolling Back and Rolling Forward
  122. Editor Integration Revolution
  123. MLX Display Bug Squashing Day
  124. MLX Runner Gets Major Model Upgrades
  125. MLX Performance Breakthrough and Anthropic Search
  126. MLX Runner Revolution and Documentation Polish
  127. Refactoring Rollercoaster and Developer Experience Wins
  128. Bug Squashing Bonanza
  129. Smooth Onboarding for New Users
  130. Polish and Perfectionism - The Art of Getting the Details Right
  131. Cleaning Up the Config Game
  132. Speed Boost and Model Magic
  133. Memory Magic and Command Makeover
  134. Making Ollama Play Nice with Everyone
  135. The Great Cleanup - Manifests Get Their Own Home
  136. New Model Architecture and Image Generation Fixes
  137. New Model Support and Memory Management Wins
  138. FLUX.2 Image Generation Arrives
  139. Image Generation Goes Native and Parser Cleanup Magic
  140. Dynamic Loading and Experimental Models Take Center Stage
  141. 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 264 episodes
  2. Pi Mono 144 episodes
  3. OpenClaw 221 episodes
  4. RuView 175 episodes
  5. Godot Daily 209 episodes
  6. Agora Next Updates 280 episodes
  7. Rails Daily 264 episodes
  8. Home Assistant Daily 269 episodes
  9. Linux Kernel Daily 242 episodes
  10. Eleviewer Daily 2 episodes
  11. React Daily 160 episodes
  12. Jabref Daily 110 episodes
  13. BlocksBeyondTheStars Daily 89 episodes
  14. Jabref Daily 111 episodes
  15. Next Js Daily 99 episodes
  16. Headroom Daily 108 episodes
  17. Agent Of Empires Daily 99 episodes
  18. Buzz Transcription 106 episodes
  19. Frigate NVR Updates 247 episodes
  20. Linux Kernel 235 episodes
  21. Homebrew 259 episodes
  22. TypeScript 148 episodes
  23. Ruby on Rails 252 episodes
  24. Redis 227 episodes
  25. Next.js 261 episodes
  26. Vue.js 199 episodes
  27. Rust 232 episodes
  28. Ruby Core Updates 255 episodes
  29. Python 245 episodes
  30. Go 245 episodes
  31. VS Code 263 episodes
  32. TailwindCSS 155 episodes
  33. Node.js 257 episodes
  34. Django 249 episodes
  35. React Native 206 episodes
  36. PostgreSQL 248 episodes
  37. Kubernetes 258 episodes
  38. LangChain 243 episodes
  39. PyTorch 262 episodes
  40. Openharness Daily 71 episodes
  41. Maestro Daily 98 episodes
  42. Videorc Daily 91 episodes
  43. Navidrome Daily 119 episodes
  44. Shannon 107 episodes
  45. iCloud Photos Downloader 37 episodes
  46. NativeScript iOS Daily 46 episodes
  47. AtomVM Daily 21 episodes
  48. Rimworld ChickenBatteryCage Daily 1 episode
  49. The Algorithm Daily 20 episodes
  50. Agora Next Daily 16 episodes
  51. Onlook Design Updates 34 episodes
  52. Energy Inc Ace Mate Learning Daily 2 episodes
  53. tiny-gpu Daily 20 episodes
  54. OpenAI Skills 52 episodes
  55. Crush Daily 1 episode
  56. ControlNet Daily 0 episodes
  57. FinceptTerminal Daily 0 episodes