Back to leaderboard

qwen3-4b-qwen3.6-plus-reasoning-distilled

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

unsloth-phi-4

LM-STUDIO MLX

llama · 4bit

Excellent

Mar 6, 2026 · Apple M4 Pro

Global Score
65 vs 82
Hardware Fit
96 vs 88
Quality Score
51 vs 80

Hardware

qwen3-4b-qwen3.6-p… unsloth-phi-4
MachineMac StudioMac mini
CPUApple M2 MaxApple M4 Pro
Cores1214
RAM96 GB64 GB
GPUApple M2 MaxApple M4 Pro
OSmacOS 26.1macOS 15.7.4
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… unsloth-phi-4
Tokens/sec99.627.4
First chunk18 ms457 ms
TTFT1.6 s457 ms
Load time4.8 sN/A
Memory usage0.3 GB7.7 GB
Memory %0%12%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

Speed
50/50
TTFT
16/20
Memory
30/30

unsloth-phi-4

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

Quality

qwen3-4b-qwen3.6-plus-r…

Reasoning
8/20
Coding
4/20
Instruction
14/20
Structured
9/15
Math
8/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Adequate Structured Output: Adequate Math: Adequate Multilingual: Strong

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
View qwen3-4b-qwen3.6-p… details | View unsloth-phi-4 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