qwen3-coder-30b-a3b-instruct-mlx
LM-STUDIO MLXqwen3_moe · 30B · 4bit
Oct 20, 2026 · Apple M1 Pro
ministral-3-14b-instruct-2512
LM-STUDIO GGUFmistral3 · 14B · Q5_K_M
Jul 4, 2026 · AMD Ryzen 7 7800X3D 8-Core Processor
Global Score
87 vs 83
Hardware Fit
85 vs 90
Quality Score
88 vs 80
Hardware
qwen3-coder-30b-a3… ministral-3-14b-in…
MachineMacBook ProASUS
CPUApple M1 ProAMD Ryzen 7 7800X3D 8-Core Processor
Cores1016
RAM32 GB31 GB
GPUApple M1 ProNVIDIA GeForce RTX 4090, Raphael
OSmacOS 15.6.1cachyos rolling
Archarm64x64
Power Modebalancedlow-power
Performance
qwen3-coder-30b-a3… ministral-3-14b-in…
Tokens/sec45.783.7
First chunk17 ms16 ms
TTFT390 ms117 ms
Load timeN/AN/A
Memory usage22.4 GB18.2 GB
Memory %70%60%
HW Fit Score Breakdown
qwen3-coder-30b-a3b-ins…
Speed
50/50
TTFT
20/20
Memory
15/30
ministral-3-14b-instruc…
Speed
50/50
TTFT
20/20
Memory
20/30
Quality
qwen3-coder-30b-a3b-ins…
Reasoning
15/20
Coding
19/20
Instruction
17/20
Structured
15/15
Math
12/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
ministral-3-14b-instruc…
Reasoning
17/20
Coding
17/20
Instruction
15/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Weak 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