richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
qwen2.5-coder:7b
OLLAMA GGUFqwen2 · 7.6B · Q4_K_M
Mar 5, 2026 · Intel Gen Intel® Core™ i7-13700K
Global Score
65 vs 68
Hardware Fit
96 vs 59
Quality Score
52 vs 72
Hardware
richardyoung/qwyth… qwen2.5-coder:7b
MachineMac miniASUS
CPUApple M4 ProIntel Gen Intel® Core™ i7-13700K
Cores1224
RAM24 GB64 GB
GPUApple M4 ProNVIDIA GeForce RTX 3070
OSmacOS 15.6.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedunknown
Performance
richardyoung/qwyth… qwen2.5-coder:7b
Tokens/sec25.334.4
First chunk397 ms1991 ms
TTFT397 ms2.0 s
Load time6.3 s40.6 s
Memory usage8.3 GB5.0 GB
Memory %34%8%
HW Fit Score Breakdown
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
qwen2.5-coder:7b
Speed
38/50
TTFT
12/20
Memory
9/30
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
qwen2.5-coder:7b
Reasoning
11/20
Coding
18/20
Instruction
12/20
Structured
13/15
Math
9/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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