google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

deepseek-r1:1.5b

OLLAMA GGUF

qwen2 · 1.8B · Q4_K_M

Good

Jun 26, 2026 · Cortex-A78AE

Global Score

71 vs 60

Hardware Fit

35 vs 90

Quality Score

86 vs 47

Hardware

google/gemma-3-27b deepseek-r1:1.5b

MachineMac miniNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super

CPUApple M4Cortex-A78AE

Cores106

RAM24 GB7 GB

GPUApple M4Integrated / Unknown

OSmacOS 26.3Ubuntu 22.04.5 LTS

Archarm64arm64

Power Modebalancedbalanced

Performance

google/gemma-3-27b deepseek-r1:1.5b

Tokens/sec5.934.6

First chunk19 ms5314 ms

TTFT1.8 s5.3 s

Load timeN/A5.1 s

Memory usage22.0 GB1.1 GB

Memory %92%15%

HW Fit Score Breakdown

google/gemma-3-27b

Speed

12/50

TTFT

19/20

Memory

4/30

deepseek-r1:1.5b

Speed

50/50

TTFT

10/20

Memory

30/30

Quality

google/gemma-3-27b

Reasoning

16/20

Coding

18/20

Instruction

16/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

deepseek-r1:1.5b

Reasoning

11/20

Coding

6/20

Instruction

7/20

Structured

4/15

Math

14/15

Multilingual

5/10

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

View google/gemma-3-27b details | View deepseek-r1:1.5b 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