mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
rnj-1:8b
OLLAMA GGUFgemma3 · 8.3B · Q4_K_M
Aug 24, 2026 · Apple M1 Pro
Global Score
80 vs 80
Hardware Fit
100 vs 93
Quality Score
71 vs 74
Hardware
mlx-community/gemm… rnj-1:8b
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
mlx-community/gemm… rnj-1:8b
Tokens/sec43.222.3
First chunk428 ms404 ms
TTFT428 ms404 ms
Load timeN/A3.7 s
Memory usage1.3 GB8.3 GB
Memory %4%52%
HW Fit Score Breakdown
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
rnj-1:8b
Speed
49/50
TTFT
20/20
Memory
24/30
Quality
mlx-community/gemma-3-4…
Reasoning
9/20
Coding
17/20
Instruction
17/20
Structured
13/15
Math
5/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak Multilingual: Strong
rnj-1:8b
Reasoning
12/20
Coding
19/20
Instruction
15/20
Structured
5/15
Math
14/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Weak Math: Strong Multilingual: Strong
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