Back to leaderboard

baidu/ernie-4.5-21b-a3b

LM-STUDIO GGUF

ernie4_5-moe · 21B · Q4_K_M

Excellent

Nov 1, 2026 · AMD RYZEN AI MAX+ 395

qwen2.5:3b

OLLAMA GGUF

qwen2 · 3.1B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score
86 vs 77
Hardware Fit
93 vs 100
Quality Score
83 vs 67

Hardware

baidu/ernie-4.5-21… qwen2.5:3b
MachineGMKtec EVO-X3NVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUAMD RYZEN AI MAX+ 395Cortex-A78AE
Cores326
RAM120 GB7 GB
GPUAMD Radeon(TM) 8060S GraphicsIntegrated / Unknown
OSMicrosoft Windows 11 Pro 10.0.26300Ubuntu 22.04.5 LTS
Archx64arm64
Power Modebalancedbalanced

Performance

baidu/ernie-4.5-21… qwen2.5:3b
Tokens/sec46.321.4
First chunk33 ms1006 ms
TTFT383 ms1.0 s
Load time49.7 s6.4 s
Memory usage32.5 GB2.0 GB
Memory %27%27%

HW Fit Score Breakdown

baidu/ernie-4.5-21b-a3b

Speed
43/50
TTFT
20/20
Memory
30/30

qwen2.5:3b

Speed
50/50
TTFT
20/20
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

qwen2.5:3b

Reasoning
12/20
Coding
14/20
Instruction
11/20
Structured
15/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View baidu/ernie-4.5-21… details | View qwen2.5:3b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest