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
gemma3:4b
OLLAMA GGUFgemma3 · 4.3B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
97 vs 76
Hardware Fit
95 vs 92
Quality Score
98 vs 69
Hardware
qwen3-30b-a3b-thin… gemma3:4b
MachineMac StudioNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M2 MaxCortex-A78AE
Cores126
RAM96 GB7 GB
GPUApple M2 MaxIntegrated / Unknown
OSmacOS 26.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… gemma3:4b
Tokens/sec79.615.0
First chunk11 ms2380 ms
TTFT1.7 s2.4 s
Load time7.1 s13.6 s
Memory usage0.0 GB2.6 GB
Memory %0%35%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
15/20
Memory
30/30
gemma3:4b
Speed
45/50
TTFT
18/20
Memory
29/30
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
gemma3:4b
Reasoning
11/20
Coding
17/20
Instruction
13/20
Structured
14/15
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