Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
gpt-oss:20b
OLLAMA GGUFgptoss · 20.9B · MXFP4
Jul 3, 2026 · AMD RYZEN AI MAX+ 395
Global Score
85 vs 94
Hardware Fit
83 vs 91
Quality Score
86 vs 95
Hardware
Kimi-48B:48B gpt-oss:20b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCFramework Desktop (AMD Ryzen AI Max 300 Series)
CPUIntel Core™ i7-14700FAMD RYZEN AI MAX+ 395
Cores2832
RAM64 GB64 GB
GPUNVIDIA GeForce RTX 5080AMD Radeon(TM) 8060S Graphics
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Pro for Workstations 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
Kimi-48B:48B gpt-oss:20b
Tokens/sec32.848.0
First chunk724 ms357 ms
TTFT724 ms2.3 s
Load time20.9 s0.2 s
Memory usage25.8 GB16.4 GB
Memory %41%26%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
gpt-oss:20b
Speed
50/50
TTFT
11/20
Memory
30/30
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-oss:20b
Reasoning
19/20
Coding
19/20
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