qwen2.5-coder:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
richardyoung/qwythos-9b-abliterated:Q8_0
OLLAMA GGUFqwen35 · 9.0B · Q8_0
Jun 28, 2026 · Apple M4 Pro
Global Score
86 vs 65
Hardware Fit
100 vs 96
Quality Score
80 vs 52
Hardware
qwen2.5-coder:14b richardyoung/qwyth…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4Mac mini
CPUIntel Core™ i5-14400FApple M4 Pro
Cores1612
RAM32 GB24 GB
GPUNVIDIA GeForce RTX 5060 TiApple M4 Pro
OSMicrosoft Windows 11 Professionnel 10.0.26200macOS 15.6.1
Archx64arm64
Power Modebalancedbalanced
Performance
qwen2.5-coder:14b richardyoung/qwyth…
Tokens/sec38.325.3
First chunk78 ms397 ms
TTFT78 ms397 ms
Load time6.3 s6.3 s
Memory usage8.8 GB8.3 GB
Memory %28%34%
HW Fit Score Breakdown
qwen2.5-coder:14b
Speed
50/50
TTFT
20/20
Memory
30/30
richardyoung/qwythos-9b…
Speed
47/50
TTFT
20/20
Memory
29/30
Quality
qwen2.5-coder:14b
Reasoning
14/20
Coding
18/20
Instruction
14/20
Structured
13/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong
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
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