Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · AMD Ryzen 9 9955HX3D 16-Core Processor
lfm2.5:latest
OLLAMA GGUFlfm2moe · 8.5B · Q4_K_M
Jun 11, 2026 · Intel Core™ i5-8350U
Global Score
85 vs 73
Hardware Fit
78 vs 93
Quality Score
88 vs 65
Hardware
Kimi-48B:48B lfm2.5:latest
MachineHP HyperX OMEN Gaming Laptop 16-ap1xxxLENOVO 20L7CTO1WW
CPUAMD Ryzen 9 9955HX3D 16-Core ProcessorIntel Core™ i5-8350U
Cores328
RAM31 GB23 GB
GPUAMD Radeon(TM) 610M, NVIDIA GeForce RTX 5070 Laptop GPUKaby Lake-R GT2 [UHD Graphics 620]
OSMicrosoft Windows 11 Home 10.0.26200Fedora Linux 44
Archx64x64
Power Modebalancedperformance
Performance
Kimi-48B:48B lfm2.5:latest
Tokens/sec42.318.3
First chunk718 ms981 ms
TTFT718 ms981 ms
Load time28.5 s8.0 s
Memory usage25.8 GB4.9 GB
Memory %83%21%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
50/50
TTFT
20/20
Memory
8/30
lfm2.5:latest
Speed
43/50
TTFT
20/20
Memory
30/30
Quality
Kimi-48B:48B
Reasoning
16/20
Coding
18/20
Instruction
15/20
Structured
15/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
lfm2.5:latest
Reasoning
2/20
Coding
11/20
Instruction
14/20
Structured
13/15
Math
15/15
Multilingual
10/10
Reasoning: Poor Coding: Adequate Instruction Following: Adequate 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