Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

llm: prevent loading too large models on windows (#5926)

Daniel Hiltgen25906d72d148
diff --git a/llm/server.go b/llm/server.go
index 41736068c..0bd94f355 100644
--- a/llm/server.go
+++ b/llm/server.go
@@ -125,8 +125,9 @@ func NewLlamaServer(gpus gpu.GpuInfoList, model string, ggml *GGML, adapters, pr
}
}
- // On linux, over-allocating CPU memory will almost always result in an error
- if runtime.GOOS == "linux" {
+ // On linux and windows, over-allocating CPU memory will almost always result in an error
+ // Darwin has fully dynamic swap so has no direct concept of free swap space
+ if runtime.GOOS != "darwin" {
systemMemoryRequired := estimate.TotalSize - estimate.VRAMSize
available := systemFreeMemory + systemSwapFreeMemory
if systemMemoryRequired > available {