richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
gemma4:e4b-it-q8_0
OLLAMA GGUFgemma4 · 8.0B · Q8_0
Aug 26, 2026 · Apple M1 Pro
Global Score
65 vs 91
Hardware Fit
96 vs 88
Quality Score
52 vs 92
Hardware
richardyoung/qwyth… gemma4:e4b-it-q8_0
MachineMac miniMacBook Pro
CPUApple M4 ProApple M1 Pro
Cores1210
RAM24 GB16 GB
GPUApple M4 ProApple M1 Pro
OSmacOS 15.6.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… gemma4:e4b-it-q8_0
Tokens/sec25.330.0
First chunk397 ms311 ms
TTFT397 ms6.2 s
Load time6.3 s6.9 s
Memory usage8.3 GB5.0 GB
Memory %34%31%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
gemma4:e4b-it-q8_0
Speed
50/50
TTFT
8/20
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
gemma4:e4b-it-q8_0
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
15/15
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