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
mistral:latest
OLLAMA GGUFllama · 7.2B · Q4_K_M
May 27, 2026 · AMD Ryzen 5 2600X Six-Core Processor
Global Score
97 vs 73
Hardware Fit
95 vs 100
Quality Score
98 vs 62
Hardware
qwen3-30b-a3b-thin… mistral:latest
MachineMac StudioMicro-Star International Co., Ltd. MS-7B79
CPUApple M2 MaxAMD Ryzen 5 2600X Six-Core Processor
Cores1212
RAM96 GB16 GB
GPUApple M2 MaxNVIDIA GeForce GTX 1080
OSmacOS 26.1Microsoft Windows 11 Famille 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… mistral:latest
Tokens/sec79.631.7
First chunk11 ms102 ms
TTFT1.7 s102 ms
Load time7.1 s14.3 s
Memory usage0.0 GB4.8 GB
Memory %0%30%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
mistral:latest
Speed
50/50
TTFT
20/20
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
mistral:latest
Reasoning
8/20
Coding
13/20
Instruction
16/20
Structured
12/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate 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