qwen3-coder-30b-a3b-instruct-mlx
LM-STUDIO MLXqwen3_moe · 30B · 4bit
Oct 20, 2026 · Apple M1 Pro
nvidia/nemotron-3-nano
LM-STUDIO MLXnemotron_h · 30B · 4bit
Mar 4, 2026 · Apple M4
Global Score
87 vs 84
Hardware Fit
85 vs 100
Quality Score
88 vs 77
Hardware
qwen3-coder-30b-a3… nvidia/nemotron-3-…
MachineMacBook ProMacBook Air
CPUApple M1 ProApple M4
Cores1010
RAM32 GB32 GB
GPUApple M1 ProApple M4
OSmacOS 15.6.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-coder-30b-a3… nvidia/nemotron-3-…
Tokens/sec45.747.9
First chunk17 ms465 ms
TTFT390 ms465 ms
Load timeN/AN/A
Memory usage22.4 GB16.6 GB
Memory %70%52%
HW Fit Score Breakdown
qwen3-coder-30b-a3b-ins…
Speed
50/50
TTFT
20/20
Memory
15/30
nvidia/nemotron-3-nano
Speed
50/50
TTFT
20/20
Memory
30/30
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
nvidia/nemotron-3-nano
Reasoning
13/20
Coding
18/20
Instruction
14/20
Structured
15/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate 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