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
llama3.1:8b
OLLAMA GGUFllama · 8.0B · Q4_K_M
Aug 25, 2026 · Apple M1 Pro
Global Score
95 vs 72
Hardware Fit
94 vs 77
Quality Score
96 vs 70
Hardware
qwen3-30b-a3b-thin… llama3.1:8b
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M1 Pro
Cores1210
RAM96 GB16 GB
GPUApple M2 MaxApple M1 Pro
OSmacOS 26.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… llama3.1:8b
Tokens/sec80.421.5
First chunk46 ms368 ms
TTFT1.8 s368 ms
Load timeN/A6.9 s
Memory usage21.2 GB12.9 GB
Memory %22%81%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
llama3.1:8b
Speed
47/50
TTFT
20/20
Memory
10/30
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
llama3.1:8b
Reasoning
12/20
Coding
18/20
Instruction
13/20
Structured
13/15
Math
4/15
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