unsloth/gemma-4-26b-a4b-it

LM-STUDIO GGUF

gemma4 · 26B · Q3_K_M

Excellent

Apr 5, 2026 · Apple M4

deepseek-r1:14b

OLLAMA GGUF

qwen2 · 14.8B · Q4_K_M

Not Rec.

Mar 2, 2026 · Apple M4

Global Score

84 vs 22

Hardware Fit

64 vs 50

Quality Score

92 vs 10

Hardware

unsloth/gemma-4-26… deepseek-r1:14b

MachineMac miniMacBook Air

CPUApple M4Apple M4

Cores1010

RAM24 GB32 GB

GPUApple M4Apple M4

OSmacOS 26.3macOS 26.3

Archarm64arm64

Power Modebalancedbalanced

Performance

unsloth/gemma-4-26… deepseek-r1:14b

Tokens/sec16.511.4

First chunk32 msN/A

TTFT2.2 s30.0 s

Load timeN/A1.0 s

Memory usage19.3 GB16.5 GB

Memory %80%52%

HW Fit Score Breakdown

unsloth/gemma-4-26b-a4b…

Speed

36/50

TTFT

18/20

Memory

10/30

deepseek-r1:14b

Speed

20/50

TTFT

0/20

Memory

30/30

Quality

unsloth/gemma-4-26b-a4b…

Reasoning

18/20

Coding

19/20

Instruction

17/20

Structured

14/15

Math

14/15

Multilingual

10/10

Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

deepseek-r1:14b

Reasoning

1/20

Coding

3/20

Instruction

1/20

Structured

0/15

Math

0/15

Multilingual

5/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Adequate

View unsloth/gemma-4-26… details | View deepseek-r1:14b 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