Back to leaderboard

google/gemma-4-12b-qat

LM-STUDIO GGUF

gemma4 · 12B · Q4_0

Excellent

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

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 19, 2026 · Intel Core™ i7-14700F

Global Score
92 vs 85
Hardware Fit
100 vs 83
Quality Score
89 vs 86

Hardware

google/gemma-4-12b… Kimi-48B:48B
MachineMicro-Star International Co., Ltd. MS-7E51HP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUAMD Ryzen 7 9700X 8-Core ProcessorIntel Core™ i7-14700F
Cores1628
RAM31 GB64 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsNVIDIA GeForce RTX 5080
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 11 Enterprise 10.0.26200
Archx64x64
Power Modebalancedbalanced

Performance

google/gemma-4-12b… Kimi-48B:48B
Tokens/sec90.732.8
First chunk26 ms724 ms
TTFT127 ms724 ms
Load timeN/A20.9 s
Memory usage6.7 GB25.8 GB
Memory %21%41%

HW Fit Score Breakdown

google/gemma-4-12b-qat

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

Kimi-48B:48B

Speed
36/50
TTFT
20/20
Memory
27/30

Quality

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

Kimi-48B:48B

Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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