qwen3:0.6b
OLLAMA GGUFqwen3 · 751.63M · Q4_K_M
Apr 29, 2026 · Intel Core™ i5-8350U
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
Global Score
61 vs 86
Hardware Fit
85 vs 78
Quality Score
51 vs 89
Hardware
qwen3:0.6b 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
qwen3:0.6b Kimi-48B:48B
Tokens/sec27.023.1
First chunk597 ms752 ms
TTFT8.7 s752 ms
Load time1.8 s22.2 s
Memory usage0.9 GB25.5 GB
Memory %4%40%
HW Fit Score Breakdown
qwen3:0.6b
Speed
50/50
TTFT
5/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
qwen3:0.6b
Reasoning
14/20
Coding
0/20
Instruction
9/20
Structured
12/15
Math
9/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Strong Math: Adequate Multilingual: Adequate
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