richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen3-1.7b
LM-STUDIO GGUFqwen3 · 1.7B · Q4_K_M
Mar 7, 2026 · Intel Core™ i5-5300U
Global Score
65 vs 19
Hardware Fit
96 vs 64
Quality Score
52 vs 0
Hardware
richardyoung/qwyth… qwen3-1.7b
MachineMac miniLENOVO 20BUS00700
CPUApple M4 ProIntel Core™ i5-5300U
Cores124
RAM24 GB16 GB
GPUApple M4 ProIntel(R) HD Graphics 5500
OSmacOS 15.6.1Microsoft Windows 10 Professionnel 10.0.19045
Archarm64x64
Power Modebalancedbalanced
Performance
richardyoung/qwyth… qwen3-1.7b
Tokens/sec25.35.9
First chunk397 ms2111 ms
TTFT397 ms2.1 s
Load time6.3 sN/A
Memory usage8.3 GB1.2 GB
Memory %34%8%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen3-1.7b
Speed
21/50
TTFT
19/20
Memory
24/30
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
0/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
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