richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Oct 11, 2026 · AMD Ryzen 5 5500
Global Score
65 vs 74
Hardware Fit
96 vs 100
Quality Score
52 vs 63
Hardware
richardyoung/qwyth… qwen3:0.6b
MachineMac miniMicrosoft WSL
CPUApple M4 ProAMD Ryzen 5 5500
Cores1212
RAM24 GB8 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 15.6.1Ubuntu 26.04.1 LTS
Archarm64x64
Power Modebalancedunknown
Performance
richardyoung/qwyth… qwen3:0.6b
Tokens/sec25.3257.7
First chunk397 ms92 ms
TTFT397 ms675 ms
Load time6.3 s4.7 s
Memory usage8.3 GB0.9 GB
Memory %34%11%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3:0.6b
Speed
50/50
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
qwen3:0.6b
Reasoning
13/20
Coding
6/20
Instruction
12/20
Structured
13/15
Math
12/15
Multilingual
7/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
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