Back to leaderboard

gemma4:26b-nvfp4

OLLAMA GGUF

nvfp4

Not Rec.

May 25, 2026 · Apple M4 Pro

deepseek-r1-distill-qwen-14b-mlx

LM-STUDIO MLX

qwen2 · 14B · 5bit

Not Rec.

Mar 11, 2026 · Apple M4

Global Score
85 vs 36
Hardware Fit
80 vs 53
Quality Score
87 vs 28

Hardware

gemma4:26b-nvfp4 deepseek-r1-distil…
MachineMacBook ProMac mini
CPUApple M4 ProApple M4
Cores1410
RAM48 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 26.4.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

gemma4:26b-nvfp4 deepseek-r1-distil…
Tokens/sec65.710.3
First chunk233 ms27 ms
TTFT30.0 s20.7 s
Load time5.0 s15.4 s
Memory usage15.2 GB1.0 GB
Memory %32%4%

HW Fit Score Breakdown

gemma4:26b-nvfp4

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

deepseek-r1-distill-qwe…

Speed
23/50
TTFT
0/20
Memory
30/30

Quality

gemma4:26b-nvfp4

Reasoning
17/20
Coding
15/20
Instruction
16/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

deepseek-r1-distill-qwe…

Reasoning
3/20
Coding
6/20
Instruction
6/20
Structured
3/15
Math
2/15
Multilingual
8/10
Reasoning: Poor Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Poor 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