Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ Ultra X7 358H
lfm2.5-thinking:1.2b
OLLAMA GGUFlfm2 · 1.2B · Q4_K_M
May 25, 2026 · Apple M4 Pro
Global Score
86 vs 60
Hardware Fit
78 vs 80
Quality Score
89 vs 52
Hardware
Kimi-48B:48B lfm2.5-thinking:1.2b
MachineGMKtec NucBox EVO-T2SMacBook Pro
CPUIntel Core™ Ultra X7 358HApple M4 Pro
Cores1614
RAM64 GB48 GB
GPUIntel(R) Arc(TM) B390 GPUApple M4 Pro
OSMicrosoft Windows 11 Pro 10.0.26200macOS 26.4.1
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B lfm2.5-thinking:1.2b
Tokens/sec22.8227.0
First chunk721 ms60 ms
TTFT721 ms30.0 s
Load time23.0 s0.7 s
Memory usage25.5 GB2.6 GB
Memory %40%6%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
lfm2.5-thinking:1.2b
Speed
50/50
TTFT
0/20
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
lfm2.5-thinking:1.2b
Reasoning
8/20
Coding
6/20
Instruction
10/20
Structured
7/15
Math
12/15
Multilingual
9/10
Reasoning: Weak Coding: Weak Instruction Following: Adequate Structured Output: Weak 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