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
gemma4:26b
OLLAMA GGUFgemma4 · 25.2B · Q4_K_M
Oct 2, 2026 · AMD Ryzen 9 5950X 16-Core Processor
Global Score
95 vs 84
Hardware Fit
94 vs 80
Quality Score
96 vs 86
Hardware
qwen3-30b-a3b-thin… gemma4:26b
MachineMac StudioSystem manufacturer
CPUApple M2 MaxAMD Ryzen 9 5950X 16-Core Processor
Cores1232
RAM96 GB32 GB
GPUApple M2 MaxNVIDIA GeForce RTX 3090
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.26300
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… gemma4:26b
Tokens/sec80.4147.6
First chunk46 ms139 ms
TTFT1.8 s30.0 s
Load timeN/A21.3 s
Memory usage21.2 GB1.7 GB
Memory %22%5%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
gemma4:26b
Speed
50/50
TTFT
0/20
Memory
30/30
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
gemma4:26b
Reasoning
17/20
Coding
14/20
Instruction
18/20
Structured
15/15
Math
13/15
Multilingual
9/10
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