Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
qwen2.5-coder:1.5b
OLLAMA GGUFqwen2 · 1.5B · Q4_K_M
Aug 28, 2026 · Intel Core™ i5-10210U
Global Score
86 vs 68
Hardware Fit
78 vs 100
Quality Score
89 vs 54
Hardware
Kimi-48B:48B qwen2.5-coder:1.5b
MachineGMKtec NucBox EVO-T2SLENOVO 20U30029MB
CPUIntel Core™ Ultra X7 358HIntel Core™ i5-10210U
Cores168
RAM64 GB15 GB
GPUIntel(R) Arc(TM) B390 GPUCometLake-U GT2 [UHD Graphics]
OSMicrosoft Windows 11 Pro 10.0.26200Pop 24.04 LTS
Archx64x64
Power Modebalancedlow-power
Performance
Kimi-48B:48B qwen2.5-coder:1.5b
Tokens/sec22.821.8
First chunk721 ms499 ms
TTFT721 ms499 ms
Load time23.0 s4.4 s
Memory usage25.5 GB1.5 GB
Memory %40%10%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
qwen2.5-coder:1.5b
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
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
qwen2.5-coder:1.5b
Reasoning
8/20
Coding
11/20
Instruction
13/20
Structured
11/15
Math
3/15
Multilingual
8/10
Reasoning: Weak Coding: Adequate Instruction Following: Adequate Structured Output: Adequate Math: Poor 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