richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3.5-4b-mlx
LM-STUDIO MLXqwen3_5 · 4B · 4bit
Mar 6, 2026 · Apple M4 Pro
Global Score
65 vs 62
Hardware Fit
96 vs 35
Quality Score
52 vs 73
Hardware
richardyoung/qwyth… qwen3.5-4b-mlx
MachineMac miniMac mini
CPUApple M4 ProApple M4 Pro
Cores1214
RAM24 GB64 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 15.6.1macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3.5-4b-mlx
Tokens/sec25.30.0
First chunk397 ms5548 ms
TTFT397 ms5.5 s
Load time6.3 sN/A
Memory usage8.3 GB2.9 GB
Memory %34%5%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3.5-4b-mlx
Speed
0/50
TTFT
6/20
Memory
29/30
Quality
richardyoung/qwythos-9b…
Reasoning
18/20
Coding
13/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor
qwen3.5-4b-mlx
Reasoning
17/20
Coding
17/20
Instruction
9/20
Structured
8/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest