Back to leaderboard

google/gemma-4-e4b

LM-STUDIO GGUF

gemma4 · 7.9B · Q4_K_M

Excellent

Sep 20, 2026 · AMD Ryzen 9 8940HX

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

Aug 19, 2026 · AMD Ryzen 7 9700X 8-Core Processor

Global Score
83 vs 92
Hardware Fit
96 vs 100
Quality Score
78 vs 89

Hardware

google/gemma-4-e4b google/gemma-4-12b…
MachineASUSTeK COMPUTER INC. ROG Strix G16 G614PH_G614PHMicro-Star International Co., Ltd. MS-7E51
CPUAMD Ryzen 9 8940HXAMD Ryzen 7 9700X 8-Core Processor
Cores3216
RAM15 GB31 GB
GPUNVIDIA GeForce RTX 5050 Laptop GPU, AMD Radeon(TM) 610MNVIDIA GeForce RTX 5080, AMD Radeon(TM) Graphics
OSMicrosoft Windows 11 Home Single Language 10.0.26200Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-e4b google/gemma-4-12b…
Tokens/sec35.990.7
First chunk9 ms26 ms
TTFT182 ms127 ms
Load timeN/AN/A
Memory usage6.5 GB6.7 GB
Memory %43%21%

HW Fit Score Breakdown

google/gemma-4-e4b

Speed
49/50
TTFT
20/20
Memory
27/30

google/gemma-4-12b-qat

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

Quality

google/gemma-4-e4b

Reasoning
14/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
6/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong

google/gemma-4-12b-qat

Reasoning
17/20
Coding
19/20
Instruction
18/20
Structured
15/15
Math
11/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

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