mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
qwen3-vl:30b
OLLAMA GGUFqwen3vlmoe · 31.1B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
72 vs 80
Hardware Fit
99 vs 98
Quality Score
61 vs 72
Hardware
mlx-community/gemm… qwen3-vl:30b
MachineMacBook AirASUS
CPUApple M4Intel Core™ Ultra 9 285K
Cores1024
RAM32 GB47 GB
GPUApple M4NVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.3Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
mlx-community/gemm… qwen3-vl:30b
Tokens/sec86.3208.9
First chunk253 ms102 ms
TTFT253 ms684 ms
Load timeN/A0.1 s
Memory usage1.1 GB22.0 GB
Memory %4%47%
HW Fit Score Breakdown
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
qwen3-vl:30b
Speed
50/50
TTFT
20/20
Memory
28/30
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
qwen3-vl:30b
Reasoning
14/20
Coding
6/20
Instruction
17/20
Structured
12/15
Math
13/15
Multilingual
10/10
Reasoning: Adequate Coding: Weak Instruction Following: Strong Structured Output: Strong 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