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

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Mar 4, 2026 · Intel Gen Intel® Core™ i7-12700K

Global Score
86 vs 80
Hardware Fit
93 vs 60
Quality Score
83 vs 88

Hardware

baidu/ernie-4.5-21… qwen3-coder:30b
MachineGMKtec EVO-X3ASUS
CPUAMD RYZEN AI MAX+ 395Intel Gen Intel® Core™ i7-12700K
Cores3220
RAM120 GB96 GB
GPUAMD Radeon(TM) 8060S GraphicsParsec Virtual Display Adapter, NVIDIA GeForce RTX 2060
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

baidu/ernie-4.5-21… qwen3-coder:30b
Tokens/sec46.314.7
First chunk33 ms796 ms
TTFT383 ms796 ms
Load time49.7 s0.2 s
Memory usage32.5 GB17.9 GB
Memory %27%19%

HW Fit Score Breakdown

baidu/ernie-4.5-21b-a3b

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

qwen3-coder:30b

Speed
14/50
TTFT
19/20
Memory
27/30

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-coder:30b

Reasoning
17/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View baidu/ernie-4.5-21… details | View qwen3-coder:30b 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