Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

llama-3.1-8b-instruct

LM-STUDIO GGUF

llama · 8B · Q8_0

Excellent

Apr 26, 2026 · AMD Ryzen 5 5500

Global Score
76 vs 81
Hardware Fit
46 vs 100
Quality Score
89 vs 73

Hardware

gemma4:31b llama-3.1-8b-instr…
MachineMacBook ProASUS
CPUApple M4 MaxAMD Ryzen 5 5500
Cores1612
RAM64 GB31 GB
GPUApple M4 MaxNavi 44 [Radeon RX 9060 XT]
OSmacOS 26.3.1Nobara Linux 43
Archarm64x64
Power Modebalancedperformance

Performance

gemma4:31b llama-3.1-8b-instr…
Tokens/sec22.435.6
First chunk565 ms52 ms
TTFT30.0 s256 ms
Load time6.9 sN/A
Memory usage43.9 GB8.6 GB
Memory %69%28%

HW Fit Score Breakdown

gemma4:31b

Speed
30/50
TTFT
0/20
Memory
16/30

llama-3.1-8b-instruct

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

Quality

gemma4:31b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
9/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong 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 gemma4:31b 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