Back to leaderboard

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

gemma4:latest

OLLAMA GGUF

gemma4 · 8.0B · Q4_K_M

Excellent

Jul 11, 2026 · AMD Ryzen 9 9950X 16-Core Processor

Global Score
81 vs 87
Hardware Fit
100 vs 75
Quality Score
73 vs 92

Hardware

llama-3.1-8b-instr… gemma4:latest
MachineASUSMicro-Star International Co., Ltd. MS-7E47
CPUAMD Ryzen 5 5500AMD Ryzen 9 9950X 16-Core Processor
Cores1232
RAM31 GB125 GB
GPUNavi 44 [Radeon RX 9060 XT]AMD Radeon(TM) Graphics, NVIDIA GeForce RTX 4080 SUPER
OSNobara Linux 43Microsoft Windows 11 Pro 10.0.26100
Archx64x64
Power Modeperformancebalanced

Performance

llama-3.1-8b-instr… gemma4:latest
Tokens/sec35.642.4
First chunk52 ms472 ms
TTFT256 ms3.8 s
Load timeN/A0.3 s
Memory usage8.6 GB12.3 GB
Memory %28%10%

HW Fit Score Breakdown

llama-3.1-8b-instruct

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

gemma4:latest

Speed
40/50
TTFT
5/20
Memory
30/30

Quality

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

gemma4:latest

Reasoning
19/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
15/15
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