Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
gemma3n:latest
OLLAMA GGUFgemma3n · 6.9B · Q4_K_M
Mar 6, 2026 · AMD EPYC 9654P 96-Core Processor
Global Score
86 vs 81
Hardware Fit
78 vs 100
Quality Score
89 vs 73
Hardware
Kimi-48B:48B gemma3n:latest
MachineGMKtec NucBox EVO-T2SSupermicro AS -2015HS-TNR
CPUIntel Core™ Ultra X7 358HAMD EPYC 9654P 96-Core Processor
Cores1664
RAM64 GB128 GB
GPUIntel(R) Arc(TM) B390 GPUGH100 [H100L 94GB], ASPEED Graphics Family, GH100 [H100L 94GB]
OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 24.04.3 LTS
Archx64x64
Power Modebalancedperformance
Performance
Kimi-48B:48B gemma3n:latest
Tokens/sec23.1108.7
First chunk752 ms333 ms
TTFT752 ms333 ms
Load time22.2 s4.5 s
Memory usage25.5 GB8.6 GB
Memory %40%7%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
gemma3n:latest
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
gemma3n:latest
Reasoning
14/20
Coding
14/20
Instruction
14/20
Structured
14/15
Math
7/15
Multilingual
10/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Strong Math: Weak 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