Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

mlx-community/quantized-gemma-2b-it

LM-STUDIO GGUF
Marginal

Mar 5, 2026 · Apple M4

Global Score
66 vs 45
Hardware Fit
40 vs 100
Quality Score
77 vs 21

Hardware

gemma4:31b mlx-community/quan…
MachineASUSTeK COMPUTER INC. GX10MacBook Air
CPUCortex-X925Apple M4
Cores2010
RAM122 GB32 GB
GPUDevice 2e12Apple M4
OSUbuntu 24.04.4 LTSmacOS 26.3
Archarm64arm64
Power Modeperformancebalanced

Performance

gemma4:31b mlx-community/quan…
Tokens/sec10.744.4
First chunk983 ms336 ms
TTFT20.3 s336 ms
Load time8.8 sN/A
Memory usage21.4 GB0.1 GB
Memory %18%0%

HW Fit Score Breakdown

gemma4:31b

Speed
10/50
TTFT
0/20
Memory
30/30

mlx-community/quantized…

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

Quality

gemma4:31b

Reasoning
14/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
10/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

mlx-community/quantized…

Reasoning
4/20
Coding
1/20
Instruction
9/20
Structured
4/15
Math
2/15
Multilingual
1/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Poor Multilingual: Poor

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