# Windows quick start: Ornith MTP OpenAI endpoint

This recipe reproduces the fast Windows laptop profile measured for
`ornith-1.0-35b-MTP-graft-down-Q4_0.gguf`:

- Windows 11 with Docker Desktop using WSL2;
- NVIDIA GPU visible to Docker (`docker run --rm --gpus all ...`);
- 8 GiB VRAM and approximately 44 GiB peak whole-system RAM in the measured
  RTX 4060 Laptop configuration;
- llama.cpp b10066 (`86a9c79f8`);
- dense and attention tensors on the GPU, MoE experts in host RAM;
- integrated MTP plus n-gram speculative decoding;
- OpenAI-compatible API on localhost only.

## 1. Prerequisites

Install or update:

1. NVIDIA Windows driver;
2. WSL2;
3. Docker Desktop with the WSL2 backend;
4. Git LFS or the Hugging Face CLI for the model download.

Confirm that Docker can see the GPU:

```powershell
docker run --rm --gpus all nvidia/cuda:12.8.1-base-ubuntu24.04 nvidia-smi
```

The validated 16K profile needs roughly 43–45 GiB of total RAM in use on the
test laptop. Close memory-heavy applications before starting on a 64 GiB
machine. An 8 GiB GPU is sufficient because `--cpu-moe` keeps the large expert
weights in host RAM.

## 2. Download the full MTP artifact

Create a model directory and an isolated virtual environment for the Hugging
Face CLI. Do not upgrade `huggingface_hub` in a shared Python installation:
new CLI releases can require a newer `click` than packages such as `gTTS`.

```powershell
New-Item -ItemType Directory -Force C:\Models\Ornith-MTP | Out-Null

$HfVenv = 'C:\Models\Ornith-MTP\.hf-cli'
py -m venv $HfVenv
& "$HfVenv\Scripts\python.exe" -m pip install --upgrade pip
& "$HfVenv\Scripts\python.exe" -m pip install "huggingface_hub[hf_xet]==1.24.0"

& "$HfVenv\Scripts\hf.exe" download `
  petr567/Ornith-1.0-35B-MTP-Strix-Halo-Hybrid-GGUF `
  ornith-1.0-35b-MTP-graft-down-Q4_0.gguf `
  --local-dir C:\Models\Ornith-MTP
```

The download is approximately 19.4 GiB. Xet may spend time scanning chunks
without continuously printing progress; leave the command running until the
PowerShell prompt returns. A partially downloaded file is resumed on the next
identical command.

This creates a real standalone copy downloaded from Hugging Face. The recipe
does not use a hard link, symbolic link, or an already installed LM Studio
model.

Expected file:

```text
C:\Models\Ornith-MTP\ornith-1.0-35b-MTP-graft-down-Q4_0.gguf
Size: 20,329,342,112 bytes (18.933 GiB)
SHA-256: 365a7c02dfd320b9696f189d6dc12bd2b0eabb9f8e58ba9fc8cab3af93c0234b
```

This clean download and endpoint flow was re-tested on Windows on 19 July
2026, including checksum verification, Docker startup, `/health`, `/v1/models`,
and `/v1/chat/completions`.

Verify it:

```powershell
(Get-FileHash `
  C:\Models\Ornith-MTP\ornith-1.0-35b-MTP-graft-down-Q4_0.gguf `
  -Algorithm SHA256).Hash.ToLowerInvariant()
```

Do not use the separate `LM Studio compatible, no integrated MTP` file for
this endpoint. It deliberately omits the speculative prediction layer.

## 3. Start the endpoint

The repository includes `run-ornith-mtp-windows.ps1`. Download it beside the
model card or copy it from this repository, then run:

```powershell
Set-ExecutionPolicy -Scope Process Bypass
.\run-ornith-mtp-windows.ps1 `
  -ModelDir C:\Models\Ornith-MTP `
  -Port 18081
```

The script pins the exact tested image:

```text
ghcr.io/ggml-org/llama.cpp@sha256:1b3d1458ccda7287feab41b8001311acc03e24cde99ec0a2908fe83830562f38
llama.cpp b10066 (86a9c79f8)
```

Equivalent direct command:

```powershell
$Image = 'ghcr.io/ggml-org/llama.cpp@sha256:1b3d1458ccda7287feab41b8001311acc03e24cde99ec0a2908fe83830562f38'
$ModelDir = 'C:\Models\Ornith-MTP'

docker run --detach --rm `
  --name ornith-mtp-api `
  --gpus all `
  --publish 127.0.0.1:18081:8080 `
  --mount "type=bind,source=$ModelDir,target=/models,readonly" `
  $Image `
  --model /models/ornith-1.0-35b-MTP-graft-down-Q4_0.gguf `
  --alias ornith-1.0-35b-mtp `
  --host 0.0.0.0 --port 8080 `
  --ctx-size 16384 --parallel 1 `
  --n-gpu-layers all --cpu-moe --no-mmap `
  --batch-size 2048 --ubatch-size 512 `
  --flash-attn on `
  --cache-type-k q8_0 --cache-type-v q8_0 `
  --jinja --metrics `
  --spec-type ngram-mod,draft-mtp `
  --spec-draft-n-max 2 `
  --spec-draft-n-min 1 `
  --spec-draft-p-min 0.20 `
  --spec-ngram-mod-n-min 48 `
  --spec-ngram-mod-n-max 64 `
  --spec-ngram-mod-n-match 24
```

The host publish address is deliberately `127.0.0.1`, not `0.0.0.0`. This
prevents unauthenticated access from the LAN. Put nginx/Caddy with TLS and an
API key in front of llama-server before exposing it to other machines.

## 4. Check readiness and API

Model loading can take tens of seconds:

```powershell
docker logs -f ornith-mtp-api
```

In another terminal:

```powershell
Invoke-RestMethod http://127.0.0.1:18081/health
Invoke-RestMethod http://127.0.0.1:18081/v1/models
```

OpenAI-compatible smoke request:

```powershell
$Body = @{
  model = 'ornith-1.0-35b-mtp'
  messages = @(
    @{ role = 'user'; content = 'Reply with exactly: READY' }
  )
  temperature = 0
  max_tokens = 64
} | ConvertTo-Json -Depth 8

$Response = Invoke-RestMethod `
  -Method Post `
  -Uri http://127.0.0.1:18081/v1/chat/completions `
  -ContentType 'application/json' `
  -Body $Body

$Response.choices[0].message
```

Use these provider values in Orion or another OpenAI client:

```text
Base URL: http://127.0.0.1:18081/v1
API key:  local-only-placeholder
Model:    ornith-1.0-35b-mtp
```

llama-server does not require the placeholder key in this localhost profile,
but many OpenAI clients require a non-empty string in their configuration.

## 5. Observe and stop

```powershell
# llama.cpp request and MTP statistics
Invoke-WebRequest http://127.0.0.1:18081/metrics -UseBasicParsing |
  Select-Object -ExpandProperty Content

# GPU telemetry
nvidia-smi `
  --query-gpu=temperature.gpu,utilization.gpu,memory.used,power.draw `
  --format=csv,noheader,nounits

# logs
docker logs --tail 100 ornith-mtp-api

# stop and release RAM/VRAM
docker stop ornith-mtp-api
```

## Expected performance on the measured laptop

RTX 4060 Laptop 8 GiB, i7-13650HX and 64 GiB RAM:

| Workload | Measured decode |
|---|---:|
| 1K prompt, ordinary output | 28.74 tok/s |
| 8K prompt, high MTP acceptance | 66.88 tok/s |
| repeated 8K code | 67.23 tok/s |

The 60–67 tok/s range requires high speculative acceptance. Ordinary agent
traffic should not be advertised as a fixed 67 tok/s minimum. The same hybrid
without speculation measured about 27–30 tok/s.

## Common problems

### `could not select device driver ... gpu`

Update Docker Desktop and the NVIDIA driver, ensure Docker uses the WSL2
backend, restart Docker Desktop, then repeat the CUDA `nvidia-smi` check.

### Container exits during model loading

Check `docker logs ornith-mtp-api`, close memory-heavy programs, and confirm at
least about 45 GiB of RAM is available for the measured profile.

### Only 1–2 tok/s

Do not replace `--cpu-moe --n-gpu-layers all` with an arbitrary partial layer
split. The rejected 15-layer split forced expert traffic across CPU/GPU memory
and reduced realistic prompt decode to about 1.2 tok/s.

### MTP flags are unknown

The image is too old or a different runtime is being used. Run:

```powershell
docker run --rm `
  ghcr.io/ggml-org/llama.cpp@sha256:1b3d1458ccda7287feab41b8001311acc03e24cde99ec0a2908fe83830562f38 `
  --version
```

It must report llama.cpp version 10066 (`86a9c79f8`) for this exact recipe.