Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
phi4:latest
OLLAMA GGUFphi3 · 14.7B · Q4_K_M
Sep 15, 2026 · Intel Core™ i5-14400F
Global Score
85 vs 85
Hardware Fit
83 vs 100
Quality Score
86 vs 79
Hardware
Kimi-48B:48B phi4:latest
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUIntel Core™ i7-14700FIntel Core™ i5-14400F
Cores2816
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5060 Ti
OSMicrosoft Windows 11 Enterprise 10.0.26200Microsoft Windows 11 Professionnel 10.0.26200
Archx64x64
Power Modebalancedbalanced
Performance
Kimi-48B:48B phi4:latest
Tokens/sec32.838.3
First chunk724 ms72 ms
TTFT724 ms72 ms
Load time20.9 s6.2 s
Memory usage25.8 GB9.1 GB
Memory %41%29%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
phi4:latest
Speed
50/50
TTFT
20/20
Memory
30/30
Quality
Kimi-48B:48B
Reasoning
16/20
Coding
17/20
Instruction
15/20
Structured
15/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong
phi4:latest
Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong 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