Back to leaderboard

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Jul 7, 2026 · Cortex-X925

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 25, 2026 · Apple M1 Pro

Global Score
66 vs 76
Hardware Fit
40 vs 100
Quality Score
77 vs 66

Hardware

gemma4:31b hf.co/empero-ai/Qw…
MachineASUSTeK COMPUTER INC. GX10MacBook Pro
CPUCortex-X925Apple M1 Pro
Cores2010
RAM122 GB16 GB
GPUDevice 2e12Apple M1 Pro
OSUbuntu 24.04.4 LTSmacOS 26.6.2
Archarm64arm64
Power Modeperformancebalanced

Performance

gemma4:31b hf.co/empero-ai/Qw…
Tokens/sec10.740.3
First chunk983 ms101 ms
TTFT20.3 s101 ms
Load time8.8 s2.7 s
Memory usage21.4 GB4.5 GB
Memory %18%28%

HW Fit Score Breakdown

gemma4:31b

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

hf.co/empero-ai/Qwen3.8…

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

hf.co/empero-ai/Qwen3.8…

Reasoning
11/20
Coding
10/20
Instruction
12/20
Structured
15/15
Math
8/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Adequate 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