baidu/ernie-4.5-21b-a3b
LM-STUDIO GGUFernie4_5-moe · 21B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
qwen3:14b
OLLAMA GGUFqwen3 · 14.8B · Q4_K_M
Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor
Global Score
86 vs 82
Hardware Fit
93 vs 90
Quality Score
83 vs 79
Hardware
baidu/ernie-4.5-21… qwen3:14b
MachineGMKtec EVO-X3Micro-Star International Co., Ltd. MS-7C37
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 9 3900X 12-Core Processor
Cores3224
RAM120 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 专业版 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
baidu/ernie-4.5-21… qwen3:14b
Tokens/sec46.374.4
First chunk33 ms324 ms
TTFT383 ms2.6 s
Load time49.7 s5.1 s
Memory usage32.5 GB9.0 GB
Memory %27%14%
HW Fit Score Breakdown
baidu/ernie-4.5-21b-a3b
Speed
43/50
TTFT
20/20
Memory
30/30
qwen3:14b
Speed
50/50
TTFT
10/20
Memory
30/30
Quality
baidu/ernie-4.5-21b-a3b
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
12/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
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
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