qwen3-30b-a3b-thinking-2507-claude-4.5-sonnet-high-reasoning-distill-mlx
LM-STUDIO MLXqwen3_moe · 30B · MXFP4
Apr 20, 2026 · Apple M2 Max
neural-chat:7b
OLLAMA GGUFllama · 7B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
97 vs 67
Hardware Fit
95 vs 96
Quality Score
98 vs 55
Hardware
qwen3-30b-a3b-thin… neural-chat:7b
MachineMac StudioMacBook Air
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… neural-chat:7b
Tokens/sec79.622.5
First chunk11 msN/A
TTFT1.7 s242 ms
Load time7.1 s0.4 s
Memory usage0.0 GB4.5 GB
Memory %0%14%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
neural-chat:7b
Speed
36/50
TTFT
30/20
Memory
30/30
Quality
qwen3-30b-a3b-thinking-…
Reasoning
19/20
Coding
19/20
Instruction
20/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
neural-chat:7b
Reasoning
7/20
Coding
9/20
Instruction
12/20
Structured
12/15
Math
7/15
Multilingual
8/10
Reasoning: Weak Coding: Weak 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