Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 24, 2026 · Intel Core™ Ultra X7 358H
falcon-h1-1.5b-instruct
LM-STUDIO GGUFfalcon-h1 · 1.5B · Q4_K_M
Mar 8, 2026 · Intel Core™ i5-5300U
Global Score
86 vs 63
Hardware Fit
78 vs 54
Quality Score
89 vs 67
Hardware
Kimi-48B:48B falcon-h1-1.5b-ins…
MachineGMKtec NucBox EVO-T2SLENOVO 20BUS00700
CPUIntel Core™ Ultra X7 358HIntel Core™ i5-5300U
Cores164
RAM64 GB16 GB
GPUIntel(R) Arc(TM) B390 GPUIntel(R) HD Graphics 5500
OSMicrosoft Windows 11 Pro 10.0.26200Microsoft Windows 10 Professionnel 10.0.19045
Archx64x64
Power Modebalancedbalanced
Performance
Kimi-48B:48B falcon-h1-1.5b-ins…
Tokens/sec23.16.6
First chunk752 ms8225 ms
TTFT752 ms8.2 s
Load time22.2 sN/A
Memory usage25.5 GB0.9 GB
Memory %40%6%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
31/50
TTFT
20/20
Memory
27/30
falcon-h1-1.5b-instruct
Speed
23/50
TTFT
6/20
Memory
25/30
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
falcon-h1-1.5b-instruct
Reasoning
13/20
Coding
14/20
Instruction
14/20
Structured
11/15
Math
7/15
Multilingual
8/10
Reasoning: Adequate Coding: Adequate Instruction Following: Adequate Structured Output: Adequate 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