Back to leaderboard

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Kimi-48B:48B

OLLAMA GGUF

kimi-linear · 49.1B · unknown

Excellent

Aug 24, 2026 · Intel Core™ Ultra X7 358H

Global Score
82 vs 86
Hardware Fit
88 vs 78
Quality Score
80 vs 89

Hardware

unsloth-phi-4 Kimi-48B:48B
MachineMac miniGMKtec NucBox EVO-T2S
CPUApple M4 ProIntel Core™ Ultra X7 358H
Cores1416
RAM64 GB64 GB
GPUApple M4 ProIntel(R) Arc(TM) B390 GPU
OSmacOS 15.7.4Microsoft Windows 11 Pro 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

unsloth-phi-4 Kimi-48B:48B
Tokens/sec27.423.1
First chunk457 ms752 ms
TTFT457 ms752 ms
Load timeN/A22.2 s
Memory usage7.7 GB25.5 GB
Memory %12%40%

HW Fit Score Breakdown

unsloth-phi-4

Speed
38/50
TTFT
20/20
Memory
30/30

Kimi-48B:48B

Speed
31/50
TTFT
20/20
Memory
27/30

Quality

unsloth-phi-4

Reasoning
15/20
Coding
19/20
Instruction
14/20
Structured
13/15
Math
9/15
Multilingual
10/10
Reasoning: Adequate Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Adequate Multilingual: Strong

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
View unsloth-phi-4 details | View Kimi-48B:48B details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest