Machine-capturedpublished

Orion Coder 7B with Ollama inside 16 GB

CLI captured model, runtime and machine metadata.

Orion Coder 7B @chen Jul 17, 2026

Manifest JSON Reproduce this Run

Speed

31.4 tok/s

Time to first token

480 ms

Peak memory

7.2 GB

Task score

—

Useful

149

7 reproductions

Reproduction command

Use the exact revision and inspect the manifest before execution.

ollama run open-lab/orion-coder-7b:q4_k_m

Environment and configuration

The comparison context that makes the result interpretable.

Hardware

MachineRTX 3060 · 12 GB

CPUIntel Core i7-12700

AcceleratorNVIDIA GeForce RTX 3060

VRAM12 GB

System memory16 GB

Operating systemWindows 11

Architecturex64

Compute APICUDA 13.0

Configuration

RuntimeOllama 0.12.1

Model revisiond4f7b92

QuantizationQ4_K_M

Context length4096

Temperature0.2

Seed19

Batch size1

Portable Run manifest

Version 1.0 of the Apache-2.0 licensed Modelverse Run schema.

{
  "schemaVersion": "1.0",
  "id": "run_orion_ollama_16gb",
  "createdAt": "2026-07-17T07:45:00.000Z",
  "model": {
    "provider": "huggingface",
    "repository": "open-lab/orion-coder-7b",
    "revision": "d4f7b92",
    "quantization": "Q4_K_M",
    "licenseSnapshot": "Apache-2.0"
  },
  "runtime": {
    "name": "Ollama",
    "version": "0.12.1",
    "command": "ollama run open-lab/orion-coder-7b:q4_k_m"
  },
  "hardware": {
    "os": "Windows 11",
    "architecture": "x64",
    "cpu": "Intel Core i7-12700",
    "systemMemoryMb": 16384,
    "accelerators": [
      {
        "vendor": "NVIDIA",
        "model": "NVIDIA GeForce RTX 3060",
        "count": 1,
        "memoryMb": 12288,
        "driverVersion": "590.20",
        "computeApi": "cuda"
      }
    ]
  },
  "task": {
    "type": "coding"
  },
  "configuration": {
    "contextLength": 4096,
    "maxGeneratedTokens": 384,
    "temperature": 0.2,
    "seed": 19,
    "batchSize": 1,
    "quantization": "Q4_K_M"
  },
  "metrics": {
    "timeToFirstTokenMs": 480,
    "tokensPerSecond": 31.4,
    "peakMemoryMb": 7372.8,
    "peakVramMb": 7270.4,
    "modelLoadTimeMs": 2940
  },
  "evidence": {
    "machineCaptured": true,
    "redactionsApplied": [],
    "artifactUrls": []
  }
}

Notes and interpretation

Confirmed fit for a 16 GB system with 12 GB VRAM.

Other Runs for Orion Coder 7B

reproduced2 months ago

Independent reproduction on RTX 4070 Ti

by @mateo · llama.cpp b5881

Speed

67.3 tok/s

TTFT

201 ms

Peak

5.9 GB

Useful

103

Standardized evaluation2 months ago

Orion Coder 7B on M3 Max · local coding suite

by @alice · MLX 0.29.2

Speed

42.8 tok/s

TTFT

318 ms

Peak

6.1 GB

Useful

187

Environment and configuration

The comparison context that makes the result interpretable.

Hardware

MachineRTX 3060 · 12 GB

CPUIntel Core i7-12700

AcceleratorNVIDIA GeForce RTX 3060

VRAM12 GB

System memory16 GB

Operating systemWindows 11

Architecturex64

Compute APICUDA 13.0

Configuration

RuntimeOllama 0.12.1

Model revisiond4f7b92

QuantizationQ4_K_M

Context length4096

Temperature0.2

Seed19

Batch size1

{ "schemaVersion": "1.0", "id": "run_orion_ollama_16gb", "createdAt": "2026-07-17T07:45:00.000Z", "model": { "provider": "huggingface", "repository": "open-lab/orion-coder-7b", "revision": "d4f7b92", "quantization": "Q4_K_M", "licenseSnapshot": "Apache-2.0" }, "runtime": { "name": "Ollama", "version": "0.12.1", "command": "ollama run open-lab/orion-coder-7b:q4_k_m" }, "hardware": { "os": "Windows 11", "architecture": "x64", "cpu": "Intel Core i7-12700", "systemMemoryMb": 16384, "accelerators": [ { "vendor": "NVIDIA", "model": "NVIDIA GeForce RTX 3060", "count": 1, "memoryMb": 12288, "driverVersion": "590.20", "computeApi": "cuda" } ] }, "task": { "type": "coding" }, "configuration": { "contextLength": 4096, "maxGeneratedTokens": 384, "temperature": 0.2, "seed": 19, "batchSize": 1, "quantization": "Q4_K_M" }, "metrics": { "timeToFirstTokenMs": 480, "tokensPerSecond": 31.4, "peakMemoryMb": 7372.8, "peakVramMb": 7270.4, "modelLoadTimeMs": 2940 }, "evidence": { "machineCaptured": true, "redactionsApplied": [], "artifactUrls": [] } }