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

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
92 vs 81
Hardware Fit
100 vs 100
Quality Score
89 vs 73

Hardware

google/gemma-4-12b… llama-3.1-8b-instr…
MachineMicro-Star International Co., Ltd. MS-7E51ASUS
CPUAMD Ryzen 7 9700X 8-Core ProcessorAMD Ryzen 5 5500
Cores1612
RAM31 GB31 GB
GPUNVIDIA GeForce RTX 5080, AMD Radeon(TM) GraphicsNavi 44 [Radeon RX 9060 XT]
OSMicrosoft Windows 11 Pro 10.0.26200Nobara Linux 43
Archx64x64
Power Modebalancedperformance

Performance

google/gemma-4-12b… llama-3.1-8b-instr…
Tokens/sec90.735.6
First chunk26 ms52 ms
TTFT127 ms256 ms
Load timeN/AN/A
Memory usage6.7 GB8.6 GB
Memory %21%28%

HW Fit Score Breakdown

google/gemma-4-12b-qat

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

llama-3.1-8b-instruct

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

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

llama-3.1-8b-instruct

Reasoning
13/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
5/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View google/gemma-4-12b… details | View llama-3.1-8b-instr… 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