Back to leaderboard

google/gemma-3-27b

LM-STUDIO MLX

gemma3 · 27B · 4bit

Not Rec.

Mar 19, 2026 · Apple M4

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

LM-STUDIO GGUF

gemma4 · 26B · Q3_K_M

Excellent

Apr 5, 2026 · Apple M4

Global Score
71 vs 84
Hardware Fit
35 vs 64
Quality Score
86 vs 92

Hardware

google/gemma-3-27b unsloth/gemma-4-26…
MachineMac miniMac mini
CPUApple M4Apple M4
Cores1010
RAM24 GB24 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

google/gemma-3-27b unsloth/gemma-4-26…
Tokens/sec5.916.5
First chunk19 ms32 ms
TTFT1.8 s2.2 s
Load timeN/AN/A
Memory usage22.0 GB19.3 GB
Memory %92%80%

HW Fit Score Breakdown

google/gemma-3-27b

Speed
12/50
TTFT
19/20
Memory
4/30

unsloth/gemma-4-26b-a4b…

Speed
36/50
TTFT
18/20
Memory
10/30

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

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

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