ollama
988 issues found
ollama ps reports ~2x SIZE and a false CPU/GPU split for memory-mapped MoE models (RAM mmap double-counted)
6/9/2026
Fail to install: Unable to find application named 'Ollama'
6/9/2026
gets error in app
6/9/2026
Ollama ps shows incorrect memory usage [MacOS]
6/9/2026
[Homebrew] llama-server binary not found error when running models on macOS (v0.30.7)
6/9/2026
Error: 500 Internal Server Error: llama-server process has terminated: exit status 0xe06d7363: NTSTATUS 0xe06d7363
6/9/2026
cancel current processing
6/9/2026
Vulkan don't used from version 0.30
6/9/2026
Tool calls should never be truncated
6/9/2026
`CACHEDIR.TAG` for models directory
6/9/2026
"Overrun of a stack-based buffer" error when running Phi4
6/9/2026
Not able to install MXL model Locally
6/9/2026
Security Disclosure: 7 Critical Vulnerabilities (SSRF, RCE, CORS, Memory Leaks) — Full Public Disclosure
6/9/2026
Security Advisory: 7 Critical Vulnerabilities in Ollama (SSRF, RCE, CORS, Memory Leaks)
6/9/2026
404 errors using Ollama with VSCode to run local models
6/9/2026
[0.30.6 Regression] RTX 3060 Laptop (sm_86) skipped — archs missing 860 in compiled architectures
6/8/2026
Ollama hermes model download failing
6/8/2026
ROCm performance regression on gfx1201 (RX 9070) between 0.24.0 and 0.30.6 on Windows 10
6/8/2026
bge-m3:latest returns NaN embeddings for specific Czech text + punctuation combinations
6/8/2026
0.30.6 Regression with 7800XT
6/8/2026