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 19, 2026 · Intel Core™ i7-14700F
Global Score
65 vs 85
Hardware Fit
88 vs 83
Quality Score
55 vs 86
Hardware
qwen3.5-2b-mlx Kimi-48B:48B
MachineMac miniHP OMEN 35L VALORANT Limited Edition Gaming Desktop PC
CPUApple M4 ProIntel Core™ i7-14700F
Cores1428
RAM64 GB64 GB
GPUApple M4 ProNVIDIA GeForce RTX 5080
OSmacOS 15.7.4Microsoft Windows 11 Enterprise 10.0.26200
Archarm64x64
Power Modebalancedbalanced
Performance
qwen3.5-2b-mlx Kimi-48B:48B
Tokens/sec48.932.8
First chunk4208 ms724 ms
TTFT4.2 s724 ms
Load timeN/A20.9 s
Memory usage1.6 GB25.8 GB
Memory %3%41%
HW Fit Score Breakdown
qwen3.5-2b-mlx
Speed
50/50
TTFT
8/20
Memory
30/30
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
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
17/20
Instruction
15/20
Structured
15/15
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