Skip to content

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

llm: looser checks for minimum memory (#5677)

Jeffrey Morganef98803d63a4
diff --git a/llm/server.go b/llm/server.go
index 8f37aa23a..ffed9fc02 100644
--- a/llm/server.go
+++ b/llm/server.go
@@ -127,7 +127,7 @@ 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" {
systemMemoryRequired := estimate.TotalSize - estimate.VRAMSize
- available := min(systemTotalMemory, systemFreeMemory+systemSwapFreeMemory)
+ available := systemFreeMemory + systemSwapFreeMemory
if systemMemoryRequired > available {
slog.Warn("model request too large for system", "requested", format.HumanBytes2(systemMemoryRequired), "available", available, "total", format.HumanBytes2(systemTotalMemory), "free", format.HumanBytes2(systemFreeMemory), "swap", format.HumanBytes2(systemSwapFreeMemory))
return nil, fmt.Errorf("model requires more system memory (%s) than is available (%s)", format.HumanBytes2(systemMemoryRequired), format.HumanBytes2(available))