richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Mar 5, 2026 · Apple M1 Max
Global Score
65 vs 90
Hardware Fit
96 vs 97
Quality Score
52 vs 87
Hardware
richardyoung/qwyth… qwen3:14b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Max
Cores1210
RAM24 GB32 GB
GPUApple M4 ProApple M1 Max
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3:14b
Tokens/sec25.324.0
First chunk397 ms300 ms
TTFT397 ms300 ms
Load time6.3 s3.6 s
Memory usage8.3 GB13.8 GB
Memory %34%43%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3:14b
Speed
47/50
TTFT
20/20
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
qwen3:14b
Reasoning
17/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong 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