baidu/ernie-4.5-21b-a3b
LM-STUDIO GGUFernie4_5-moe · 21B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · 7.9B · Q4_K_M
Nov 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 80
Hardware Fit
93 vs 83
Quality Score
83 vs 79
Hardware
baidu/ernie-4.5-21… google/gemma-4-e4b
MachineGMKtec EVO-X3GMKtec EVO-X3
CPUAMD RYZEN AI MAX+ 395AMD RYZEN AI MAX+ 395
Cores3232
RAM120 GB120 GB
GPUAMD Radeon(TM) 8060S GraphicsAMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modebalancedbalanced
Performance
baidu/ernie-4.5-21… google/gemma-4-e4b
Tokens/sec46.346.5
First chunk33 ms14 ms
TTFT383 ms1.9 s
Load time49.7 s7.6 s
Memory usage32.5 GB0.0 GB
Memory %27%0%
HW Fit Score Breakdown
baidu/ernie-4.5-21b-a3b
Speed
43/50
TTFT
20/20
Memory
30/30
google/gemma-4-e4b
Speed
43/50
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
google/gemma-4-e4b
Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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