richardyoung/qwythos-9b-abliterated:Q8_0

qwen35 · 9.0B · Q8_0

Mac mini (Apple M4 Pro)

24 GB · macOS 15.6.1

Tested on June 28, 2026 · Submitted by Tram

Top 64% Compare

Global Score

65 /100

Good

Hardware Fit

96/100

Quality

52/100

Get this model

🦙

Ollama

ollama pull richardyoung/qwythos-9b-abliterated:Q8_0

View on Ollama Library

ollama.com/library/richardyoung/qwythos-9b-abliterated

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Mac mini
CPU: Apple M4 Pro
Cores: 12 total (8 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 24 GB LPDDR5
GPU: Apple M4 Pro
OS: macOS 15.6.1
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 25.3
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 397 ms
Time to first token How fast the model starts responding — lower is better: 397 ms
Load time Time to load the model into memory before inference: 6.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 8.3 GB (34%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429

Score breakdown

Speed

47/50

Time to first token

20/20

Memory

29/30

Quality

Reasoning

18/20

Coding

13/20

Instruction following

6/20

Structured output

0/15

Math

14/15

Multilingual

1/10

Category levels

Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.30.11
Model format: GGUF
Hardware profile: BALANCED
Result hash: e33901f6c637a6a43329e31da54afecefb2bdf39a7e01939da5d912a58f8febb

Interpretation

Hardware fit: 96/100. Overall suitability: GOOD (Global 65/100). Category profile: Reasoning: Strong, Coding: Adequate, Instruction Following: Weak, Structured Output: Poor, Math: Strong, Multilingual: Poor.

Bench Environment

Power: AC Swap delta: +0.1 GB CPU load: avg 12% (peak 13%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest