Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Oct 31, 2026 · AMD RYZEN AI MAX+ 395

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Excellent

Jun 13, 2026 · AMD Ryzen 9 3900X 12-Core Processor

Global Score
81 vs 82
Hardware Fit
84 vs 90
Quality Score
79 vs 79

Hardware

google/gemma-4-e4b qwen3:14b
MachineGMKtec EVO-X3Micro-Star International Co., Ltd. MS-7C37
CPUAMD RYZEN AI MAX+ 395AMD Ryzen 9 3900X 12-Core Processor
Cores3224
RAM120 GB64 GB
GPUAMD Radeon(TM) 8060S GraphicsGameViewer Virtual Display Adapter, NVIDIA GeForce RTX 3080
OSMicrosoft Windows 11 Pro 10.0.26300Microsoft Windows 11 专业版 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b qwen3:14b
Tokens/sec47.374.4
First chunk23 ms324 ms
TTFT1.9 s2.6 s
Load timeN/A5.1 s
Memory usage13.2 GB9.0 GB
Memory %11%14%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
44/50
TTFT
10/20
Memory
30/30

qwen3:14b

Speed
50/50
TTFT
10/20
Memory
30/30

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

qwen3:14b

Reasoning
18/20
Coding
11/20
Instruction
17/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View google/gemma-4-e4b details | View qwen3:14b 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