Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
GPT-20B:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
Global Score
85 vs 90
Hardware Fit
83 vs 79
Quality Score
86 vs 94
Hardware
Kimi-48B:48B GPT-20B:20b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCHP HyperX OMEN Gaming Laptop 16-ap1xxx
CPUIntel Core™ i7-14700FAMD Ryzen 9 9955HX3D 16-Core Processor
Cores2832
RAM64 GB31 GB
GPUNVIDIA GeForce RTX 5080AMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPU
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Home 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
Kimi-48B:48B GPT-20B:20b
Tokens/sec32.836.6
First chunk724 ms722 ms
TTFT724 ms4.7 s
Load time20.9 s0.3 s
Memory usage25.8 GB13.1 GB
Memory %41%42%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
GPT-20B:20b
Speed
46/50
TTFT
6/20
Memory
27/30
Quality
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
GPT-20B:20b
Reasoning
19/20
Coding
18/20
Instruction
17/20
Structured
15/15
Math
15/15
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