mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
yi:6b
OLLAMA GGUFllama · 6B · Q4_0
Mar 1, 2026 · Apple M4
Global Score
72 vs 77
Hardware Fit
99 vs 100
Quality Score
61 vs 67
Hardware
mlx-community/gemm… yi:6b
MachineMacBook AirMacBook Air
CPUApple M4Apple M4
Cores1010
RAM32 GB32 GB
GPUApple M4Apple M4
OSmacOS 26.3macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/gemm… yi:6b
Tokens/sec86.327.6
First chunk253 msN/A
TTFT253 ms210 ms
Load timeN/A0.4 s
Memory usage1.1 GB3.6 GB
Memory %4%11%
HW Fit Score Breakdown
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
yi:6b
Speed
40/50
TTFT
30/20
Memory
30/30
Quality
mlx-community/gemma-3-1…
Reasoning
7/20
Coding
14/20
Instruction
16/20
Structured
14/15
Math
2/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Strong Structured Output: Strong Math: Poor Multilingual: Strong
yi:6b
Reasoning
11/20
Coding
12/20
Instruction
13/20
Structured
12/15
Math
13/15
Multilingual
6/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Adequate
Run yours and compare
$
npm install -g metrillm@latest$
metrillmRequires Node 20+ and Ollama or LM Studio running
Or run without installing: npx metrillm@latest