Back to leaderboard

phi-3-mini-128k-instruct

LM-STUDIO MLX

phi3 · 4bit

Not Rec.

Mar 4, 2026 · Apple M4

hf.co/empero-ai/Qwen3.8-2B-Distill-GGUF:BF16

OLLAMA GGUF

qwen35 · 1.94B · BF16

Good

Aug 23, 2026 · Apple M1 Pro

Global Score
38 vs 66
Hardware Fit
100 vs 100
Quality Score
12 vs 52

Hardware

phi-3-mini-128k-in… hf.co/empero-ai/Qw…
MachineMacBook AirMacBook Pro
CPUApple M4Apple M1 Pro
Cores1010
RAM32 GB16 GB
GPUApple M4Apple M1 Pro
OSmacOS 26.3macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

phi-3-mini-128k-in… hf.co/empero-ai/Qw…
Tokens/sec44.040.4
First chunk384 ms93 ms
TTFT385 ms93 ms
Load timeN/A2.7 s
Memory usage2.0 GB4.7 GB
Memory %6%30%

HW Fit Score Breakdown

phi-3-mini-128k-instruct

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

hf.co/empero-ai/Qwen3.8…

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

Quality

phi-3-mini-128k-instruct

Reasoning
3/20
Coding
2/20
Instruction
2/20
Structured
1/15
Math
2/15
Multilingual
2/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

hf.co/empero-ai/Qwen3.8…

Reasoning
15/20
Coding
9/20
Instruction
8/20
Structured
1/15
Math
15/15
Multilingual
4/10
Reasoning: Adequate Coding: Weak Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Weak
View phi-3-mini-128k-in… details | View hf.co/empero-ai/Qw… 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