foundry CLI crashes in GPU

[uranio-235]

After load the model qwen3.5-9b-generic-gpu

In a

AMD Ryzen 7 5800H with Radeon Graphics (3.20 GHz)
16,0 GB (12,9 GB usable)

Foundry local CLI (pre-relase foundry-0.10.0-win-x64.msix) crashes

Note: the model was loaded before

PS C:\Users\lazar> foundry server logs
── daemon ── foundrylocald-2026-06-18.log ──
2026-06-18T07:57:21.172Z [INF] Foundry.Daemon.Startup: Binding IPC server
2026-06-18T07:57:21.173Z [INF] Foundry.Daemon.Ipc.IpcServer: IPC server listening at foundry-cli-S-1-5-21-7058110-2118780955-1158885348-1001.
2026-06-18T07:57:21.173Z [INF] Foundry.Daemon.Startup: Starting heartbeat publisher (cadence=00:00:05)
2026-06-18T07:57:21.173Z [INF] Foundry.Daemon.Startup: Activating noise suppressor
2026-06-18T07:57:21.174Z [INF] Foundry.Daemon.Startup: Calling FoundryLocalManager.CreateAsync
2026-06-18T07:57:21.373Z [INF] Foundry.Daemon.Startup: Downloading and registering EPs
2026-06-18T07:57:23.680Z [INF] Foundry.Daemon.Startup: Starting SDK web service
2026-06-18T07:57:23.693Z [INF] Foundry.Daemon.Startup: Writing daemon discovery file (1 URLs)
2026-06-18T07:57:23.695Z [INF] Foundry.Daemon.Startup: Daemon Ready
2026-06-18T08:25:06.031Z [INF] Foundry.Daemon.Startup: Binding IPC server
2026-06-18T08:25:06.032Z [INF] Foundry.Daemon.Ipc.IpcServer: IPC server listening at foundry-cli-S-1-5-21-7058110-2118780955-1158885348-1001.
2026-06-18T08:25:06.032Z [INF] Foundry.Daemon.Startup: Starting heartbeat publisher (cadence=00:00:05)
2026-06-18T08:25:06.032Z [INF] Foundry.Daemon.Startup: Activating noise suppressor
2026-06-18T08:25:06.032Z [INF] Foundry.Daemon.Startup: Calling FoundryLocalManager.CreateAsync
2026-06-18T08:25:06.333Z [INF] Foundry.Daemon.Startup: Downloading and registering EPs
2026-06-18T08:25:08.090Z [INF] Foundry.Daemon.Startup: Starting SDK web service
2026-06-18T08:25:08.101Z [INF] Foundry.Daemon.Startup: Writing daemon discovery file (1 URLs)
2026-06-18T08:25:08.113Z [INF] Foundry.Daemon.Startup: Daemon Ready

── sdk (managed) ── foundry20260617.log ──
2026-06-17 20:54:33.296 +01:00 [INF] Starting Foundry Local CLI with ''

── sdk (native) ── foundry.core20260618.log ──
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x749
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x871
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<>c__DisplayClass0_0.<<HandleStreamRequest>b__0>d.MoveNext() + 0x67
--- End of stack trace from previous location ---
   at
Microsoft.AspNetCore.Http.Generated.<GeneratedRouteBuilderExtensions_g>F0ECBE2C0C7D34979467E85EF7818A838D2B03F1D4DAE97FB49706AFC5213297B__GeneratedRouteBuilderExtensionsCore.<>c__DisplayClass7_0.<<MapPost3>g__
RequestHandler|5>d.MoveNext() + 0x110
--- End of stack trace from previous location ---
   at Microsoft.AspNetCore.Routing.EndpointMiddleware.<<Invoke>g__AwaitRequestTask|7_0>d.MoveNext() + 0x5a
--- End of stack trace from previous location ---
   at Microsoft.AspNetCore.Server.Kestrel.Core.Internal.Http.HttpProtocol.<ProcessRequests>d__238`1.MoveNext() + 0x2f2
2026-06-18 09:26:10.091 +01:00 [ERR] Connection id "0HNMD2CH7E9JU", Request id "0HNMD2CH7E9JU:00000001": An unhandled exception was thrown by the application.
System.InvalidOperationException: Model 'qwen3.5-9b-generic-gpu' is not loaded. Please load the model before getting a ChatClient.
   at Microsoft.AI.Foundry.Local.FoundryLocalCore.<GetChatClientAsync>d__41.MoveNext() + 0x273
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIApiProvider.<HandleChatCompletionAsStreamRequestAsync>d__5.MoveNext() + 0x11c
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x430
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x749
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x871
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<>c__DisplayClass0_0.<<HandleStreamRequest>b__0>d.MoveNext() + 0x67
--- End of stack trace from previous location ---
   at
Microsoft.AspNetCore.Http.Generated.<GeneratedRouteBuilderExtensions_g>F0ECBE2C0C7D34979467E85EF7818A838D2B03F1D4DAE97FB49706AFC5213297B__GeneratedRouteBuilderExtensionsCore.<>c__DisplayClass7_0.<<MapPost3>g__
RequestHandler|5>d.MoveNext() + 0x110
--- End of stack trace from previous location ---
   at Microsoft.AspNetCore.Routing.EndpointMiddleware.<<Invoke>g__AwaitRequestTask|7_0>d.MoveNext() + 0x5a
--- End of stack trace from previous location ---
   at Microsoft.AspNetCore.Server.Kestrel.Core.Internal.Http.HttpProtocol.<ProcessRequests>d__238`1.MoveNext() + 0x2f2
2026-06-18 09:26:14.864 +01:00 [ERR] Connection id "0HNMD2CH7E9JV", Request id "0HNMD2CH7E9JV:00000001": An unhandled exception was thrown by the application.
System.InvalidOperationException: Model 'qwen3.5-9b-generic-gpu' is not loaded. Please load the model before getting a ChatClient.
   at Microsoft.AI.Foundry.Local.FoundryLocalCore.<GetChatClientAsync>d__41.MoveNext() + 0x273
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIApiProvider.<HandleChatCompletionAsStreamRequestAsync>d__5.MoveNext() + 0x11c
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x430
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x749
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<WriteChatCompletionResponses>d__3.MoveNext() + 0x871
--- End of stack trace from previous location ---
   at Microsoft.AI.Foundry.Local.Service.OpenAIServiceExtensions.<>c__DisplayClass0_0.<<HandleStreamRequest>b__0>d.MoveNext() + 0x67
--- End of stack trace from previous location ---
   at
Microsoft.AspNetCore.Http.Generated.<GeneratedRouteBuilderExtensions_g>F0ECBE2C0C7D34979467E85EF7818A838D2B03F1D4DAE97FB49706AFC5213297B__GeneratedRouteBuilderExtensionsCore.<>c__DisplayClass7_0.<<MapPost3>g__
RequestHandler|5>d.MoveNext() + 0x110
--- End of stack trace from previous location ---
   at Microsoft.AspNetCore.Routing.EndpointMiddleware.<<Invoke>g__AwaitRequestTask|7_0>d.MoveNext() + 0x5a
--- End of stack trace from previous location ---
   at Microsoft.AspNetCore.Server.Kestrel.Core.Internal.Http.HttpProtocol.<ProcessRequests>d__238`1.MoveNext() + `0x2f2`