Kimi-48B:48B
OLLAMA GGUFkimi-linear · 49.1B · unknown
Aug 19, 2026 · Intel Core™ i7-14700F
phi3:3.8b
OLLAMA GGUFphi3 · 3.8B · Q4_0
Mar 2, 2026 · Apple M4
Global Score
85 vs 64
Hardware Fit
83 vs 100
Quality Score
86 vs 48
Hardware
Kimi-48B:48B phi3:3.8b
MachineHP OMEN 35L VALORANT Limited Edition Gaming Desktop PCMacBook Air
CPUIntel Core™ i7-14700FApple M4
Cores2810
RAM64 GB32 GB
GPUNVIDIA GeForce RTX 5080Apple M4
OSMicrosoft Windows 11 Enterprise 10.0.26200macOS 26.3
Archx64arm64
Power Modebalancedbalanced
Performance
Kimi-48B:48B phi3:3.8b
Tokens/sec32.842.0
First chunk724 msN/A
TTFT724 ms142 ms
Load time20.9 s1.1 s
Memory usage25.8 GB16.0 GB
Memory %41%50%
HW Fit Score Breakdown
Kimi-48B:48B
Speed
36/50
TTFT
20/20
Memory
27/30
phi3:3.8b
Speed
40/50
TTFT
30/20
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
phi3:3.8b
Reasoning
12/20
Coding
3/20
Instruction
11/20
Structured
10/15
Math
5/15
Multilingual
7/10
Reasoning: Adequate Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Weak Multilingual: Adequate
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