qwen2.5-coder:14b
OLLAMA GGUFqwen2 · 14.8B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
mistralai/ministral-3-3b
LM-STUDIO GGUFmistral3 · 3B · Q4_K_M
Oct 31, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 76
Hardware Fit
100 vs 94
Quality Score
80 vs 68
Hardware
qwen2.5-coder:14b mistralai/ministra…
MachineGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4GMKtec EVO-X3
CPUIntel Core™ i5-14400FAMD RYZEN AI MAX+ 395
Cores1632
RAM32 GB120 GB
GPUNVIDIA GeForce RTX 5060 TiAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 11 Professionnel 10.0.26200Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced
Performance
qwen2.5-coder:14b mistralai/ministra…
Tokens/sec38.350.2
First chunk78 ms6 ms
TTFT78 ms726 ms
Load time6.3 sN/A
Memory usage8.8 GB19.6 GB
Memory %28%16%
HW Fit Score Breakdown
qwen2.5-coder:14b
Speed
50/50
TTFT
20/20
Memory
30/30
mistralai/ministral-3-3b
Speed
46/50
TTFT
18/20
Memory
30/30
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
mistralai/ministral-3-3b
Reasoning
10/20
Coding
16/20
Instruction
15/20
Structured
15/15
Math
3/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Poor 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