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
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 22, 2026 · NVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Global Score
95 vs 90
Hardware Fit
94 vs 96
Quality Score
96 vs 88
Hardware
qwen3-30b-a3b-thin… Kimi-48B:48B
MachineMac StudioHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M2 MaxNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1220
RAM96 GB55 GB
GPUApple M2 MaxNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 26.1Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3-30b-a3b-thin… Kimi-48B:48B
Tokens/sec80.462.7
First chunk46 ms397 ms
TTFT1.8 s397 ms
Load timeN/A16.8 s
Memory usage21.2 GB25.5 GB
Memory %22%47%
HW Fit Score Breakdown
qwen3-30b-a3b-thinking-…
Speed
50/50
TTFT
14/20
Memory
30/30
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
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
Kimi-48B:48B
Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
12/15
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