REAL LOCAL SUITES · CODING V2 + COMPREHENSIVE · SUITES NOT MIXED
AVAILABLE/PARTIAL PERFORMANCE
OLLAMA LOCAL REGISTRY
fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b
gguf · Q4_K_M · 4.2B
Capability scoreNOT TESTEDReal performance benchmark available
NORMALIZED IDENTITY
Digest-bound metadata
- Registry name
- fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b
- Namespace
- fredrezones55
- Base name
- Qwen3.5-Uncensored-HauhauCS-Aggressive
- Tag
- 4b
- Family
- qwen35
- Parameters
- 4.2B
- Quantization
- Q4_K_M
- Disk size
- 2.52 GB
- Architecture
- qwen35
- Confidence
- digest bound
- Digest
- a7871357408218f2f3f9e03c975d1fbda50cf658318c58867c2e9336309b855e
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
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
- Model
- fredrezones55/Qwen3.5-Uncensored-HauhauCS-Aggressive:4b
- Quantization
- Q4_K_M
- 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
- 4468.35 msrequest → first visible token; may include loading
- Cold load duration
- 4083.32 msseparately reported by Ollama
- Cold generation
- 19.10 tok/s · VALID
- Cold E2E
- 11170.23 ms
- Warm median TTFT
- 306.48 msresident model: request → first visible token
- Warm median generation
- 18.39 tok/s
- Small prompt median
- not collected
- Medium prompt median
- not collected
STATISTICAL STABILITY
Median is the primary display value
| Metric | Valid/total | Median | Mean | P25 | P75 | Min | Max | Std dev | Outliers |
|---|---|---|---|---|---|---|---|---|---|
| Warm medium generationVALID | 5/5 | 18.39 tok/s | 18.20 tok/s | 17.95 tok/s | 18.42 tok/s | 17.20 tok/s | 19.03 tok/s | 0.61 tok/s | 1 |
| Warm medium TTFTVALID | 5/5 | 306.48 ms | 302.09 ms | 297.55 ms | 311.93 ms | 279.92 ms | 314.57 ms | 12.52 ms | 0 |
| Small prompt processingNOT_COLLECTED | 0/3 | not collected | not collected | not collected | not collected | not collected | not collected | not collected | 0 |
| Medium prompt processingNOT_COLLECTED | 0/3 | not collected | not collected | not collected | not collected | not collected | not collected | not collected | 0 |
MEMORY
Passive observations with explicit sources
| Point | System free | System available | System used | Process RAM | Ollama residency VRAM |
|---|---|---|---|---|---|
| Before | 0.07 GiBsystem_api | not collectednot_collected | 15.93 GiBsystem_api | not collectednot_collected | 0.00 GiBollama_api · residency, not peak |
| After load | 0.11 GiBsystem_api | not collectednot_collected | 15.89 GiBsystem_api | not collectednot_collected | 3.67 GiBollama_api · residency, not peak |
| After unload | 5.16 GiBsystem_api | not collectednot_collected | 10.84 GiBsystem_api | not collectednot_collected | 0.00 GiBollama_api · residency, not peak |
RAW TRIALS
14 retained trials
Expand every cold, warm, generation, and prompt-processing trial
| Trial | Kind | Profile | State | Tokens | TTFT | Prompt tok/s | Generation tok/s | Validity | Outlier |
|---|---|---|---|---|---|---|---|---|---|
| trial-01 | generation | MEDIUM | cold | 128 / 128 | 4468.35 ms | not collected | 19.10 tok/s | VALID | no |
| trial-02 | generation | MEDIUM | warm | 128 / 128 | 314.57 ms | not collected | 19.03 tok/s | VALID | no |
| trial-03 | generation | MEDIUM | warm | 128 / 128 | 306.48 ms | not collected | 18.42 tok/s | VALID | no |
| trial-04 | generation | MEDIUM | warm | 128 / 128 | 279.92 ms | not collected | 17.95 tok/s | VALID | no |
| trial-05 | generation | MEDIUM | warm | 128 / 128 | 311.93 ms | not collected | 18.39 tok/s | VALID | no |
| trial-06 | generation | MEDIUM | warm | 128 / 128 | 297.55 ms | not collected | 17.20 tok/s | VALID | POTENTIAL OUTLIER |
| trial-07 | generation | SHORT | warm | 32 / 32 | 314.62 ms | not collected | 18.50 tok/s | VALID | no |
| trial-08 | generation | LONG | warm | 256 / 256 | 282.71 ms | not collected | 18.14 tok/s | VALID | no |
| trial-09 | prompt_processing | PROMPT_SMALL | warm | 4 / 4 | 841.63 ms | not collected | 23.90 tok/s | VALID | no |
| trial-10 | prompt_processing | PROMPT_SMALL | warm | 4 / 4 | 295.13 ms | not collected | 23.63 tok/s | VALID | no |
| trial-11 | prompt_processing | PROMPT_SMALL | warm | 4 / 4 | 289.45 ms | not collected | 24.05 tok/s | VALID | no |
| trial-12 | prompt_processing | PROMPT_MEDIUM | warm | 4 / 4 | 3802.38 ms | not collected | 23.70 tok/s | VALID | no |
| trial-13 | prompt_processing | PROMPT_MEDIUM | warm | 4 / 4 | 295.89 ms | not collected | 24.08 tok/s | VALID | no |
| trial-14 | prompt_processing | PROMPT_MEDIUM | warm | 4 / 4 | 302.87 ms | not collected | 22.64 tok/s | VALID | no |
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.