qwen3-coder:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Jun 19, 2026 · Apple M4 Max
mlx-community/gemma-3-1b-it-8bit
LM-STUDIO GGUFMar 5, 2026 · Apple M4
Global Score
89 vs 72
Hardware Fit
96 vs 99
Quality Score
86 vs 61
Hardware
qwen3-coder:30b mlx-community/gemm…
MachineMacBook ProMacBook Air
CPUApple M4 MaxApple M4
Cores1610
RAM64 GB32 GB
GPUApple M4 MaxApple M4
OSmacOS 26.5.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-coder:30b mlx-community/gemm…
Tokens/sec89.986.3
First chunk188 ms253 ms
TTFT188 ms253 ms
Load time4.0 sN/A
Memory usage30.2 GB1.1 GB
Memory %47%4%
HW Fit Score Breakdown
qwen3-coder:30b
Speed
50/50
TTFT
20/20
Memory
26/30
mlx-community/gemma-3-1…
Speed
50/50
TTFT
20/20
Memory
29/30
Quality
qwen3-coder:30b
Reasoning
14/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
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
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