Back to leaderboard

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
82 vs 36
Hardware Fit
88 vs 100
Quality Score
80 vs 8

Hardware

unsloth-phi-4 qwen36-distill-apex
MachineMac miniMacBook Pro
CPUApple M4 ProApple M5 Max
Cores1418
RAM64 GB64 GB
GPUApple M4 ProApple M5 Max
OSmacOS 15.7.4macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

unsloth-phi-4 qwen36-distill-apex
Tokens/sec27.455.2
First chunk457 ms210 ms
TTFT457 ms210 ms
Load timeN/A4.8 s
Memory usage7.7 GB0.9 GB
Memory %12%2%

HW Fit Score Breakdown

unsloth-phi-4

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

qwen36-distill-apex

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

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

qwen36-distill-apex

Reasoning
8/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View unsloth-phi-4 details | View qwen36-distill-apex 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