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:26b
OLLAMA GGUFgemma4 · 25.8B · Q4_K_M
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
95 vs 90
Hardware Fit
94 vs 89
Quality Score
96 vs 90
Hardware
qwen3-30b-a3b-thin… Gemma4-26B:26b
MachineMac StudioHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUApple M2 MaxAMD Ryzen 9 9955HX3D 16-Core Processor
Cores1232
RAM96 GB31 GB
GPUApple M2 MaxAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSmacOS 26.1Microsoft Windows 11 Home 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… Gemma4-26B:26b
Tokens/sec80.439.2
First chunk46 ms1484 ms
TTFT1.8 s1.5 s
Load timeN/A42.1 s
Memory usage21.2 GB17.0 GB
Memory %22%55%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
Gemma4-26B:26b
Speed
49/50
TTFT
17/20
Memory
23/30
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:26b
Reasoning
17/20
Coding
19/20
Instruction
17/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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