qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 22, 2026 · Apple M2 Max
qwen3:30b
OLLAMA GGUFqwen3moe · 30.5B · Q4_K_M
Mar 5, 2026 · Intel Core™ Ultra 9 285K
Global Score
95 vs 86
Hardware Fit
94 vs 98
Quality Score
96 vs 81
Hardware
qwen3-30b-a3b-thin… qwen3:30b
MachineMac StudioASUS
CPUApple M2 MaxIntel Core™ Ultra 9 285K
Cores1224
RAM96 GB47 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5090, Intel(R) Graphics
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… qwen3:30b
Tokens/sec80.4204.8
First chunk46 ms96 ms
TTFT1.8 s674 ms
Load timeN/A5.2 s
Memory usage21.2 GB20.5 GB
Memory %22%43%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
qwen3:30b
Speed
50/50
TTFT
20/20
Memory
28/30
Quality
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
18/20
Instruction
19/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
qwen3:30b
Reasoning
16/20
Coding
12/20
Instruction
17/20
Structured
12/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Adequate 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