ollama
871 issues found
model load timeout
6/2/2026
context utilization not accurate
6/2/2026
Performance regression in Ollama v0.30 on 5x GTX 1070 Ti: much slower than v0.24, low GPU clocks/utilization
6/2/2026
GPT-OSS 120B not working with 0.30
6/2/2026
GGUF models doesnt'work anymore
6/2/2026
0.30.0 a half cooked release for mac users?
6/2/2026
0.30.0 Projector by using shared memory on CPU ?
6/2/2026
Conflict between ollama and VSCode
6/2/2026
llama.ccp openvino
6/2/2026
After upgrading to version 0.30.0, GPU cannot be used under AMD platforms.
6/2/2026
0.30.0 breaks opencode integration
6/2/2026
0.30.0 breaks macOS
6/2/2026
Since updating to version 0.30.0, all models on my AMD Ryzen AI 9 HX 370 now run exclusively on the CPU.
6/2/2026
403 Forbidden for certain User-agents?
6/2/2026
what version is needed to run LFM2.5-8B-A1B ?
6/2/2026
Performance decrease on Beelink GTR9 Pro AMD Ryzen™ AI Max+ 395
6/2/2026
ollama launch opencode generates invalid OpenCode config when local models have context length but no max output tokens
6/2/2026
qwen3.6 occasionally violates its own tool-call template; qwen3.5 parser returns 500 instead of tolerating the drift
6/1/2026
[Feature Request] Memory Poisoning Protection for Ollama Agents via OWASP Agent Memory Guard
6/1/2026
valkan 在 rog幻x 这样笔记本无法使用
6/1/2026