richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
gemma4:31b
OLLAMA GGUFgemma4 · 31.3B · Q4_K_M
Apr 13, 2026 · Apple M4 Max
Global Score
65 vs 76
Hardware Fit
96 vs 46
Quality Score
52 vs 89
Hardware
richardyoung/qwyth… gemma4:31b
MachineMac miniMacBook Pro
CPUApple M4 ProApple M4 Max
Cores1216
RAM24 GB64 GB
GPUApple M4 ProApple M4 Max
OSmacOS 15.6.1macOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… gemma4:31b
Tokens/sec25.322.4
First chunk397 ms565 ms
TTFT397 ms30.0 s
Load time6.3 s6.9 s
Memory usage8.3 GB43.9 GB
Memory %34%69%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
gemma4:31b
Speed
30/50
TTFT
0/20
Memory
16/30
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
gemma4:31b
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
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