google/gemma-4-e4b
LM-STUDIO GGUFgemma4 · 7.9B · Q4_K_M
Oct 31, 2026 · AMD RYZEN AI MAX+ 395
phi4-mini:latest
OLLAMA GGUFphi3 · 3.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
81 vs 74
Hardware Fit
84 vs 98
Quality Score
79 vs 63
Hardware
google/gemma-4-e4b phi4-mini:latest
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
google/gemma-4-e4b phi4-mini:latest
Tokens/sec47.318.4
First chunk23 ms1078 ms
TTFT1.9 s1.1 s
Load timeN/A6.4 s
Memory usage13.2 GB2.9 GB
Memory %11%39%
HW Fit Score Breakdown
google/gemma-4-e4b
Speed
44/50
TTFT
10/20
Memory
30/30
phi4-mini:latest
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
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
phi4-mini:latest
Reasoning
13/20
Coding
11/20
Instruction
14/20
Structured
11/15
Math
5/15
Multilingual
9/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate 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