Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
laguna-xs-2.1
OLLAMA GGUFAug 1, 2026 · AMD RYZEN AI MAX+ 395
Global Score
86 vs 84
Hardware Fit
78 vs 100
Quality Score
89 vs 77
Hardware
Kimi-48B:48B laguna-xs-2.1
MachineGMKtec NucBox EVO-T2SAZW GTR Pro
CPUIntel Core™ Ultra X7 358HAMD RYZEN AI MAX+ 395
Cores1632
RAM64 GB125 GB
GPUIntel(R) Arc(TM) B390 GPURadeon 8060S
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.4 LTS
Archx64x64
Power Modebalancedlow-power
Performance
Kimi-48B:48B laguna-xs-2.1
Tokens/sec23.165.9
First chunk752 ms281 ms
TTFT752 ms281 ms
Load time22.2 s9.9 s
Memory usage25.5 GB30.1 GB
Memory %40%24%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
laguna-xs-2.1
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
laguna-xs-2.1
Reasoning
8/20
Coding
18/20
Instruction
16/20
Structured
14/15
Math
11/15
Multilingual
10/10
Reasoning: Weak Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate 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