gptoss · 20.9B · MXFP4
OLLAMA GGUFgptoss · 20.9 · MXFP4
Jul 9, 2026 · Intel Core™ i5-10400
Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
Global Score
84 vs 86
Hardware Fit
69 vs 78
Quality Score
91 vs 89
Hardware
gptoss · 20.9B · M… Kimi-48B:48B
MachineMac ProGMKtec NucBox EVO-T2S
CPUIntel Core™ i5-10400Intel Core™ Ultra X7 358H
Cores1216
RAM32 GB64 GB
GPUAMD Radeon RX 6700 XTIntel(R) Arc(TM) B390 GPU
OSmacOS 26.5.1Microsoft Windows 11 Pro 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
gptoss · 20.9B · M… Kimi-48B:48B
Tokens/sec17.522.8
First chunk643 ms721 ms
TTFT7.7 s721 ms
Load time0.0 s23.0 s
Memory usage0.8 GB25.5 GB
Memory %3%40%
HW Fit Score Breakdown
gptoss · 20.9B · MXFP4
Speed
34/50
TTFT
5/20
Memory
30/30
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
Quality
gptoss · 20.9B · MXFP4
Reasoning
19/20
Coding
19/20
Instruction
13/20
Structured
15/15
Math
15/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong
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