Back to leaderboard

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

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 23, 2026 · Apple M1 Pro

gemma4:31b

OLLAMA GGUF

gemma4 · 31.3B · Q4_K_M

Not Rec.

Apr 13, 2026 · Apple M4 Max

Global Score
66 vs 76
Hardware Fit
100 vs 46
Quality Score
52 vs 89

Hardware

hf.co/empero-ai/Qw… gemma4:31b
MachineMacBook ProMacBook Pro
CPUApple M1 ProApple M4 Max
Cores1016
RAM16 GB64 GB
GPUApple M1 ProApple M4 Max
OSmacOS 26.6.2macOS 26.3.1
Archarm64arm64
Power Modebalancedbalanced

Performance

hf.co/empero-ai/Qw… gemma4:31b
Tokens/sec40.422.4
First chunk93 ms565 ms
TTFT93 ms30.0 s
Load time2.7 s6.9 s
Memory usage4.7 GB43.9 GB
Memory %30%69%

HW Fit Score Breakdown

hf.co/empero-ai/Qwen3.8…

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

gemma4:31b

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

Quality

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak

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
View hf.co/empero-ai/Qw… details | View gemma4:31b 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