richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3.8-27b-mlx
LM-STUDIO MLXqwen3_5 · 27B · 8bit
Aug 17, 2026 · Apple M5 Max
Global Score
65 vs 59
Hardware Fit
96 vs 63
Quality Score
52 vs 58
Hardware
richardyoung/qwyth… qwen3.8-27b-mlx
MachineMac miniMacBook Pro
CPUApple M4 ProApple M5 Max
Cores1218
RAM24 GB64 GB
GPUApple M4 ProApple M5 Max
OSmacOS 15.6.1macOS 27.0
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3.8-27b-mlx
Tokens/sec25.318.3
First chunk397 ms4 ms
TTFT397 ms530 ms
Load time6.3 sN/A
Memory usage8.3 GB38.5 GB
Memory %34%60%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3.8-27b-mlx
Speed
23/50
TTFT
20/20
Memory
20/30
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
qwen3.8-27b-mlx
Reasoning
19/20
Coding
14/20
Instruction
6/20
Structured
1/15
Math
13/15
Multilingual
5/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
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