richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3:1.7b
OLLAMA GGUFqwen3 · 2.0B · Q4_K_M
Oct 12, 2026 · AMD Ryzen 5 5500
Global Score
65 vs 76
Hardware Fit
96 vs 100
Quality Score
52 vs 65
Hardware
richardyoung/qwyth… qwen3:1.7b
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… qwen3:1.7b
Tokens/sec25.3161.3
First chunk397 ms51 ms
TTFT397 ms51 ms
Load time6.3 s5.2 s
Memory usage8.3 GB1.6 GB
Memory %34%21%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3:1.7b
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
qwen3:1.7b
Reasoning
7/20
Coding
10/20
Instruction
11/20
Structured
15/15
Math
14/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate 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