richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3:4b
OLLAMA GGUFqwen3 · 4.0B · Q4_K_M
Mar 1, 2026 · Apple M4
Global Score
65 vs 47
Hardware Fit
96 vs 53
Quality Score
52 vs 45
Hardware
richardyoung/qwyth… qwen3:4b
MachineMac miniMacBook Air
CPUApple M4 ProApple M4
Cores1210
RAM24 GB32 GB
GPUApple M4 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedunknown
Performance
richardyoung/qwyth… qwen3:4b
Tokens/sec25.311.3
First chunk397 msN/A
TTFT397 ms9.2 s
Load time6.3 s0.1 s
Memory usage8.3 GB7.2 GB
Memory %34%23%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3:4b
Speed
17/50
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
qwen3:4b
Reasoning
4/20
Coding
6/20
Instruction
8/20
Structured
6/15
Math
12/15
Multilingual
9/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Weak 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