qwen3.5:2b
OLLAMA GGUFqwen35 · 2.3B · Q8_0
Apr 29, 2026 · Intel Core™ i5-8350U
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
13 vs 86
Hardware Fit
41 vs 78
Quality Score
1 vs 89
Hardware
qwen3.5:2b Kimi-48B:48B
MachineLENOVO 20L7CTO1WWGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-8350UIntel Core™ Ultra X7 358H
Cores816
RAM23 GB64 GB
GPUKaby Lake-R GT2 [UHD Graphics 620]Intel(R) Arc(TM) B390 GPU
OSFedora Linux 43Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modelow-powerbalanced
Performance
qwen3.5:2b Kimi-48B:48B
Tokens/sec4.522.8
First chunk1413 ms721 ms
TTFT31.1 s721 ms
Load time7.1 s23.0 s
Memory usage3.8 GB25.5 GB
Memory %16%40%
HW Fit Score Breakdown
qwen3.5:2b
Speed
11/50
TTFT
0/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
qwen3.5:2b
Reasoning
0/20
Coding
0/20
Instruction
1/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
Kimi-48B:48B
Reasoning
18/20
Coding
19/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
9/10
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