Back to leaderboard

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

gemma4:e2b

OLLAMA GGUF

gemma4 · 5.1B · Q4_K_M

Good

May 24, 2026 · Intel Gen Intel® Core™ i7-1355U

Global Score
81 vs 72
Hardware Fit
100 vs 71
Quality Score
73 vs 72

Hardware

llama-3.1-8b-instr… gemma4:e2b
MachineASUSDell Inc. Inspiron 15 3530
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i7-1355U
Cores1212
RAM31 GB31 GB
GPUNavi 44 [Radeon RX 9060 XT]Raptor Lake-P [Iris Xe Graphics]
OSNobara Linux 43cachyos rolling
Archx64x64
Power Modeperformancelow-power

Performance

llama-3.1-8b-instr… gemma4:e2b
Tokens/sec35.610.8
First chunk52 ms1408 ms
TTFT256 ms1.4 s
Load timeN/A6.0 s
Memory usage8.6 GB7.2 GB
Memory %28%23%

HW Fit Score Breakdown

llama-3.1-8b-instruct

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

gemma4:e2b

Speed
21/50
TTFT
20/20
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:e2b

Reasoning
10/20
Coding
16/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak 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