qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
granite3.1-moe:3b
OLLAMA GGUFgranitemoe · 3.3B · Q4_K_M
May 24, 2026 · Intel Gen Intel® Core™ i7-1355U
Global Score
82 vs 66
Hardware Fit
90 vs 99
Quality Score
79 vs 52
Hardware
qwen3:14b granite3.1-moe:3b
MachineMicro-Star International Co., Ltd. MS-7C37Dell Inc. Inspiron 15 3530
CPUAMD Ryzen 9 3900X 12-Core ProcessorIntel Gen Intel® Core™ i7-1355U
Cores2412
RAM64 GB31 GB
GPUGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080Raptor Lake-P [Iris Xe Graphics]
OSMicrosoft Windows 11 专业版 10.0.26200cachyos rolling
Archx64x64
Power Modebalancedlow-power
Performance
qwen3:14b granite3.1-moe:3b
Tokens/sec74.427.2
First chunk324 ms527 ms
TTFT2.6 s527 ms
Load time5.1 s1.9 s
Memory usage9.0 GB2.9 GB
Memory %14%9%
HW Fit Score Breakdown
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
granite3.1-moe:3b
Speed
49/50
TTFT
20/20
Memory
30/30
Quality
qwen3:14b
Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
granite3.1-moe:3b
Reasoning
7/20
Coding
9/20
Instruction
13/20
Structured
12/15
Math
5/15
Multilingual
6/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Adequate
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