REAL LOCAL SUITES · CODING V2 + COMPREHENSIVE · SUITES NOT MIXED
AVAILABLE/PARTIAL PERFORMANCE

OLLAMA LOCAL REGISTRY

moondream:latest

gguf · Q4_0 · 1B

Capability scoreNOT TESTEDReal performance benchmark available

NORMALIZED IDENTITY

Digest-bound metadata

Registry name
moondream:latest
Namespace
none
Base name
moondream
Tag
latest
Family
phi2
Parameters
1B
Quantization
Q4_0
Disk size
1.62 GB
Architecture
phi2
Confidence
digest bound
Digest
55fc3abd386771e5b5d1bbcc732f3c3f4df6e9f9f08f1131f9cc27ba2d1eec5b

QUEUE POSITION

Not queued

Queue mode
PLANNING ONLY
Item status
not queued
Execution enabled
FALSE
Attempts
0

PLANNED BENCHMARK SUITES

Recorded for a future authorized run

PLAN ONLY
PerformanceChineseEnglishReasoningMathCodingInstruction FollowingStructured OutputAnswer QualityLong Context

IDENTITY RELATIONSHIPS

No relationships detected

No same-digest alias, exact content duplicate, or metadata-matched variant candidate was found.

REAL PERFORMANCE RUN

PARTIAL · HeavryBench Performance v1

CAPABILITY NOT TESTED
Model
moondream:latest
Quantization
Q4_0
Hardware
Apple M4
Ollama
0.30.9
Prompt version
Performance Prompt v1
Methodology
HeavryBench Performance v1
Classification
REAL_PERFORMANCE_RUN
Leaderboard
INELIGIBLE

SPEED

Cold and warm measurements

Cold TTFT
2432.82 msrequest → first visible token; may include loading
Cold load duration
2113.50 msseparately reported by Ollama
Cold generation
114.70 tok/s · INSUFFICIENT_SAMPLE
Cold E2E
2527.18 ms
Warm median TTFT
43.52 msresident model: request → first visible token
Warm median generation
not collected
Small prompt median
not collected
Medium prompt median
not collected

STATISTICAL STABILITY

Median is the primary display value

HeavryBench IQR Outliers v1
MetricValid/totalMedianMeanP25P75MinMaxStd devOutliers
Warm medium generationINSUFFICIENT_SAMPLE0/5not collectednot collectednot collectednot collectednot collectednot collectednot collected0
Warm medium TTFTVALID5/543.52 ms48.28 ms43.40 ms44.23 ms42.52 ms67.75 ms9.75 ms1
Small prompt processingNOT_COLLECTED0/3not collectednot collectednot collectednot collectednot collectednot collectednot collected0
Medium prompt processingNOT_COLLECTED0/3not collectednot collectednot collectednot collectednot collectednot collectednot collected0

MEMORY

Passive observations with explicit sources

PointSystem freeSystem availableSystem usedProcess RAMOllama residency VRAM
Before0.07 GiBsystem_apinot collectednot_collected15.93 GiBsystem_apinot collectednot_collected0.00 GiBollama_api · residency, not peak
After load0.09 GiBsystem_apinot collectednot_collected15.91 GiBsystem_apinot collectednot_collected1.19 GiBollama_api · residency, not peak
After unload0.23 GiBsystem_apinot collectednot_collected15.77 GiBsystem_apinot collectednot_collected0.00 GiBollama_api · residency, not peak

RAW TRIALS

14 retained trials

Expand every cold, warm, generation, and prompt-processing trial
TrialKindProfileStateTokensTTFTPrompt tok/sGeneration tok/sValidityOutlier
trial-01generationMEDIUMcold11 / 1282432.82 msnot collected114.70 tok/sINSUFFICIENT_SAMPLEno
trial-02generationMEDIUMwarm11 / 12867.75 msnot collected114.11 tok/sINSUFFICIENT_SAMPLEno
trial-03generationMEDIUMwarm11 / 12844.23 msnot collected113.61 tok/sINSUFFICIENT_SAMPLEno
trial-04generationMEDIUMwarm11 / 12843.52 msnot collected108.52 tok/sINSUFFICIENT_SAMPLEno
trial-05generationMEDIUMwarm11 / 12843.40 msnot collected114.86 tok/sINSUFFICIENT_SAMPLEno
trial-06generationMEDIUMwarm11 / 12842.52 msnot collected105.20 tok/sINSUFFICIENT_SAMPLEno
trial-07generationSHORTwarm11 / 3244.30 msnot collected111.42 tok/sINSUFFICIENT_SAMPLEno
trial-08generationLONGwarm11 / 25643.13 msnot collected114.02 tok/sINSUFFICIENT_SAMPLEno
trial-09prompt_processingPROMPT_SMALLwarm4 / 4139.64 msnot collected126.96 tok/sVALIDno
trial-10prompt_processingPROMPT_SMALLwarm4 / 445.25 msnot collected121.32 tok/sVALIDno
trial-11prompt_processingPROMPT_SMALLwarm4 / 445.44 msnot collected135.30 tok/sVALIDno
trial-12prompt_processingPROMPT_MEDIUMwarm4 / 4762.00 msnot collected123.90 tok/sVALIDno
trial-13prompt_processingPROMPT_MEDIUMwarm4 / 447.96 msnot collected125.16 tok/sVALIDno
trial-14prompt_processingPROMPT_MEDIUMwarm4 / 448.23 msnot collected121.71 tok/sVALIDno

SAFETY & REPRODUCIBILITY

Cleanup verified

Before / during / after
0 / 1 / 0
Target absent after
true
Digest matched
true
Reproducibility
partial
CAPABILITY: NOT TESTED

HeavryBench Score and all Chinese, Reasoning, Math, Coding, Knowledge, Instruction Following, and Long Context fields remain null.