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
deepseek-r1:1.5b
OLLAMA GGUFqwen2 · 1.8B · Q4_K_M
Jun 26, 2026 · Cortex-A78AE
Global Score
95 vs 60
Hardware Fit
94 vs 90
Quality Score
96 vs 47
Hardware
qwen3-30b-a3b-thin… deepseek-r1:1.5b
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… deepseek-r1:1.5b
Tokens/sec80.434.6
First chunk46 ms5314 ms
TTFT1.8 s5.3 s
Load timeN/A5.1 s
Memory usage21.2 GB1.1 GB
Memory %22%15%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
deepseek-r1:1.5b
Speed
50/50
TTFT
10/20
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
deepseek-r1:1.5b
Reasoning
11/20
Coding
6/20
Instruction
7/20
Structured
4/15
Math
14/15
Multilingual
5/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Weak
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