qwen3.5-2b-mlx
LM-STUDIO MLXqwen3_5 · 2B · 4bit
Mar 6, 2026 · Apple M4 Pro
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
65 vs 90
Hardware Fit
88 vs 96
Quality Score
55 vs 88
Hardware
qwen3.5-2b-mlx Kimi-48B:48B
MachineMac miniHP HyperX OMEN Transcend Gaming Laptop 14-ga0xxx5CD612DXML
CPUApple M4 ProNVIDIA RTX Spark N1X (6144-core GPU, 20-core ) RTX Spark N1X (6144-core GPU, 20-core )
Cores1420
RAM64 GB55 GB
GPUApple M4 ProNVIDIA RTX Spark N1X (6144-core Blackwell RTX GPU), NVIDIA NPU
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.28000
Archarm64arm64
Power Modebalancedbalanced
Performance
qwen3.5-2b-mlx Kimi-48B:48B
Tokens/sec48.962.7
First chunk4208 ms397 ms
TTFT4.2 s397 ms
Load timeN/A16.8 s
Memory usage1.6 GB25.5 GB
Memory %3%47%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
8/20
Memory
30/30
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
26/30
Quality
qwen3.5-2b-mlx
Reasoning
10/20
Coding
7/20
Instruction
13/20
Structured
14/15
Math
3/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Strong Math: Poor 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