Verified October 17, 2026. Firsthand Kingy test evidence.
LM Studio 0.4.26+4; llama.cpp Metal engine 2.60.0. Existing artifact SHA-256: 7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5.
The runtime returned its specific model-lookup error for the supplied identifier. This does not diagnose a missing GGUF, an allocation failure or an HTTP route mismatch.
{
"error": {
"message": "Invalid model identifier \"kingy-memory-missing-20261017\". Please specify a valid downloaded model (e.g., qwen3-4b).",
"type": "invalid_request",
"param": "model",
"code": "model_not_found"
}
}Inspect GET /api/v1/models or lms ps and select the exact loaded instance identifier. In this retained case, kingy-memory-lms was already loaded; changing only the request model field restored the task.
Repeat the unchanged original task with the known local model and require all expected facts. Record the actual model identity and response; an HTTP 200 alone is insufficient.
{
"start_code": "ALPHA-17",
"middle_code": "BRAVO-42",
"end_code": "CHARLIE-93"
}| Attempt | HTTP | Task accepted | Seconds |
|---|---|---|---|
| baseline 1 | 404 | False | 0.03 |
| baseline 2 | 404 | False | 0.0 |
| baseline 3 | 404 | False | 0.0 |
| shared corrected 1 | 200 | True | 2.41 |
| shared corrected 2 | 200 | True | 0.9 |
| shared corrected 3 | 200 | True | 0.86 |
| reverted | 404 | False | 0.06 |
Same agent, one Apple M4 Pro Mac with 24 GiB unified RAM, one Qwen3-4B Q4_K_M artifact. No independent human or second-machine reproduction.
Three baseline failures, three corrected exact-task passes and one reverted failure per repair. The two repairs for each runtime share the identical three corrected attempts; these are six unique corrected generations total, not twelve.
Fixed synthetic task, not a reliability estimate or proof for other models, versions or hardware. No real OOM condition was induced. No Ollama or LM Studio memory-fit calibration is claimed.
Existing weights were reused, with no model download or paid inference. A free official Ollama portable runtime was added; runtime binaries and weights are excluded from the evidence ZIP.
The earlier CPU-only cohort is unqualified: two corrected passes followed by a 120-second timeout. It remains in the evidence. The qualified cohort kept Metal GPU offload fixed across its conditions.
Native /api/v1/chat exposes no finish_reason. Acceptance required strict exact JSON, all original facts, zero reported reasoning tokens and reported output below the 128-token cap; no observed stop marker is claimed.
Download requests, raw responses, protocol and audit. Runtime binaries, private logs, model weights and user data are excluded.
API reference: LM Studio native chat, LM Studio CLI. These references describe the API; the attempt files establish the observed results.