Machine-capturedpublished

Sparrow Chat 3B on a CPU-only laptop

Machine-captured CPU-only Run with attached logs.

Sparrow Chat 3B @mateo Jul 20, 2026

Manifest JSON Reproduce this Run

Speed

12.6 tok/s

Time to first token

901 ms

Peak memory

3.4 GB

Task score

—

Useful

210

9 reproductions

Reproduction command

Use the exact revision and inspect the manifest before execution.

llama-cli -m sparrow-chat-3b-q4_k_m.gguf -p 'Hello' -n 256

Environment and configuration

The comparison context that makes the result interpretable.

Hardware

Machine16 GB Linux laptop · CPU only

CPUAMD Ryzen 7 7840U

AcceleratorCPU

VRAM0 GB

System memory16 GB

Operating systemFedora 43

Architecturex64

Configuration

Runtimellama.cpp b5881

Model revision5dc3ef1

QuantizationQ4_K_M

Context length4096

Temperature0.7

Seed71

Batch size1

Portable Run manifest

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

{
  "schemaVersion": "1.0",
  "id": "run_sparrow_cpu",
  "createdAt": "2026-07-20T07:15:00.000Z",
  "model": {
    "provider": "huggingface",
    "repository": "local-ai/sparrow-chat-3b",
    "revision": "5dc3ef1",
    "quantization": "Q4_K_M",
    "licenseSnapshot": "Apache-2.0"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b5881",
    "command": "llama-cli -m sparrow-chat-3b-q4_k_m.gguf -p 'Hello' -n 256"
  },
  "hardware": {
    "os": "Fedora 43",
    "architecture": "x64",
    "cpu": "AMD Ryzen 7 7840U",
    "systemMemoryMb": 16384,
    "accelerators": []
  },
  "task": {
    "type": "chat"
  },
  "configuration": {
    "contextLength": 4096,
    "maxGeneratedTokens": 256,
    "temperature": 0.7,
    "seed": 71,
    "batchSize": 1,
    "quantization": "Q4_K_M"
  },
  "metrics": {
    "timeToFirstTokenMs": 901,
    "tokensPerSecond": 12.6,
    "peakMemoryMb": 3481.6,
    "modelLoadTimeMs": 2190
  },
  "evidence": {
    "machineCaptured": true,
    "redactionsApplied": [],
    "artifactUrls": []
  }
}

Notes and interpretation

Useful baseline for machines without a discrete GPU.

Other Runs for Sparrow Chat 3B

reproduced2 months ago

Sparrow Chat 3B on 8 GB M1 MacBook Air

by @alice · Ollama 0.12.1

Speed

18.9 tok/s

TTFT

651 ms

Peak

3.5 GB

Useful

177

Environment and configuration

The comparison context that makes the result interpretable.

Hardware

Machine16 GB Linux laptop · CPU only

CPUAMD Ryzen 7 7840U

AcceleratorCPU

VRAM0 GB

System memory16 GB

Operating systemFedora 43

Architecturex64

Configuration

Runtimellama.cpp b5881

Model revision5dc3ef1

QuantizationQ4_K_M

Context length4096

Temperature0.7

Seed71

Batch size1

{ "schemaVersion": "1.0", "id": "run_sparrow_cpu", "createdAt": "2026-07-20T07:15:00.000Z", "model": { "provider": "huggingface", "repository": "local-ai/sparrow-chat-3b", "revision": "5dc3ef1", "quantization": "Q4_K_M", "licenseSnapshot": "Apache-2.0" }, "runtime": { "name": "llama.cpp", "version": "b5881", "command": "llama-cli -m sparrow-chat-3b-q4_k_m.gguf -p 'Hello' -n 256" }, "hardware": { "os": "Fedora 43", "architecture": "x64", "cpu": "AMD Ryzen 7 7840U", "systemMemoryMb": 16384, "accelerators": [] }, "task": { "type": "chat" }, "configuration": { "contextLength": 4096, "maxGeneratedTokens": 256, "temperature": 0.7, "seed": 71, "batchSize": 1, "quantization": "Q4_K_M" }, "metrics": { "timeToFirstTokenMs": 901, "tokensPerSecond": 12.6, "peakMemoryMb": 3481.6, "modelLoadTimeMs": 2190 }, "evidence": { "machineCaptured": true, "redactionsApplied": [], "artifactUrls": [] } }