Back to leaderboard

phi4-mini:latest

OLLAMA GGUF

phi3 · 3.8B · Q4_K_M

Good

Nov 4, 2026 · Intel Core™ i7-9700

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

Global Score
75 vs 86
Hardware Fit
84 vs 93
Quality Score
71 vs 83

Hardware

phi4-mini:latest baidu/ernie-4.5-21…
MachineVMware, Inc. VMware Virtual PlatformGMKtec EVO-X3
CPUIntel Core™ i7-9700AMD RYZEN AI MAX+ 395
Cores432
RAM16 GB120 GB
GPUIntegrated / UnknownAMD Radeon(TM) 8060S Graphics
OSUbuntu 24.04.5 LTSMicrosoft Windows 11 Pro 10.0.26300
Archx64x64
Power Modeunknownbalanced

Performance

phi4-mini:latest baidu/ernie-4.5-21…
Tokens/sec10.846.3
First chunk643 ms33 ms
TTFT643 ms383 ms
Load time31.5 s49.7 s
Memory usage2.9 GB32.5 GB
Memory %19%27%

HW Fit Score Breakdown

phi4-mini:latest

Speed
34/50
TTFT
20/20
Memory
30/30

baidu/ernie-4.5-21b-a3b

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

Quality

phi4-mini:latest

Reasoning
13/20
Coding
14/20
Instruction
15/20
Structured
14/15
Math
6/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

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
View phi4-mini:latest details | View baidu/ernie-4.5-21… 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