mlx-community/gemma-3-4b-it-qat-4bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
devstral:latest
OLLAMA GGUFllama · 23.6B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
80 vs 80
Hardware Fit
100 vs 79
Quality Score
71 vs 80
Hardware
mlx-community/gemm… devstral:latest
MachineMacBook AirGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M4Intel Core™ i5-14400F
Cores1016
RAM32 GB32 GB
GPUApple M4NVIDIA GeForce RTX 5060 Ti
OSmacOS 26.3Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
mlx-community/gemm… devstral:latest
Tokens/sec43.220.0
First chunk428 ms146 ms
TTFT428 ms146 ms
Load timeN/A6.5 s
Memory usage1.3 GB14.2 GB
Memory %4%45%
HW Fit Score Breakdown
mlx-community/gemma-3-4…
Speed
50/50
TTFT
20/20
Memory
30/30
devstral:latest
Speed
33/50
TTFT
20/20
Memory
26/30
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
devstral:latest
Reasoning
16/20
Coding
17/20
Instruction
13/20
Structured
15/15
Math
9/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate 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