Back to leaderboard

falcon3-1b-instruct

LM-STUDIO MLX

llama · 1B · 3bit

Marginal

Mar 4, 2026 · Apple M4

gemma-3-27b-it-qat

LM-STUDIO MLX

gemma3 · 27B · 4bit

Good

Mar 5, 2026 · Apple M4 Pro

Global Score
54 vs 76
Hardware Fit
100 vs 51
Quality Score
34 vs 87

Hardware

falcon3-1b-instruct gemma-3-27b-it-qat
MachineMacBook AirMac mini
CPUApple M4Apple M4 Pro
Cores1014
RAM32 GB64 GB
GPUApple M4Apple M4 Pro
OSmacOS 26.3macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

falcon3-1b-instruct gemma-3-27b-it-qat
Tokens/sec121.88.9
First chunk176 ms3976 ms
TTFT176 ms4.0 s
Load timeN/AN/A
Memory usage0.7 GB15.7 GB
Memory %2%25%

HW Fit Score Breakdown

falcon3-1b-instruct

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

gemma-3-27b-it-qat

Speed
12/50
TTFT
9/20
Memory
30/30

Quality

falcon3-1b-instruct

Reasoning
7/20
Coding
1/20
Instruction
12/20
Structured
7/15
Math
2/15
Multilingual
5/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Weak Math: Poor Multilingual: Weak

gemma-3-27b-it-qat

Reasoning
16/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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