Back to leaderboard

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

google/gemma-4-e4b-it-qat

LM-STUDIO GGUF

gemma4 · Q4_0

Good

Jun 29, 2026 · Intel Gen Intel® Core™ i9-11900H

Global Score
81 vs 78
Hardware Fit
100 vs 68
Quality Score
73 vs 82

Hardware

llama-3.1-8b-instr… google/gemma-4-e4b…
MachineASUSDocker Container
CPUAMD Ryzen 5 5500Intel Gen Intel® Core™ i9-11900H
Cores1216
RAM31 GB15 GB
GPUNavi 44 [Radeon RX 9060 XT]TigerLake-H GT1 [UHD Graphics]
OSNobara Linux 43Ubuntu 26.04 LTS
Archx64x64
Power Modeperformanceperformance

Performance

llama-3.1-8b-instr… google/gemma-4-e4b…
Tokens/sec35.611.4
First chunk52 ms26 ms
TTFT256 ms2.2 s
Load timeN/A5.9 s
Memory usage8.6 GB0.0 GB
Memory %28%0%

HW Fit Score Breakdown

llama-3.1-8b-instruct

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

google/gemma-4-e4b-it-qat

Speed
21/50
TTFT
17/20
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

google/gemma-4-e4b-it-qat

Reasoning
14/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View llama-3.1-8b-instr… details | View google/gemma-4-e4b… 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