richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3:8b
OLLAMA GGUFqwen3 · 8.2B · Q4_K_M
Mar 2, 2026 · Apple M4
Global Score
65 vs 47
Hardware Fit
96 vs 67
Quality Score
52 vs 38
Hardware
richardyoung/qwyth… qwen3:8b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1210
RAM24 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3:8b
Tokens/sec25.318.7
First chunk397 msN/A
TTFT397 ms12.1 s
Load time6.3 s1.2 s
Memory usage8.3 GB9.5 GB
Memory %34%30%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3:8b
Speed
31/50
TTFT
6/20
Memory
30/30
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
qwen3:8b
Reasoning
5/20
Coding
5/20
Instruction
4/20
Structured
12/15
Math
2/15
Multilingual
10/10
Reasoning: Weak Coding: Weak Instruction Following: Poor Structured Output: Strong Math: Poor 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