Back to leaderboard

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

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

phi4:latest

OLLAMA GGUF

phi3 · 14.7B · Q4_K_M

Excellent

Sep 15, 2026 · Intel Core™ i5-14400F

Global Score
65 vs 85
Hardware Fit
96 vs 100
Quality Score
51 vs 79

Hardware

qwen3-4b-qwen3.6-p… phi4:latest
MachineMac StudioGigabyte Technology Co., Ltd. B760 AORUS ELITE AX DDR4
CPUApple M2 MaxIntel Core™ i5-14400F
Cores1216
RAM96 GB32 GB
GPUApple M2 MaxNVIDIA GeForce RTX 5060 Ti
OSmacOS 26.1Microsoft Windows 11 Professionnel 10.0.26200
Archarm64x64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… phi4:latest
Tokens/sec99.638.3
First chunk18 ms72 ms
TTFT1.6 s72 ms
Load time4.8 s6.2 s
Memory usage0.3 GB9.1 GB
Memory %0%29%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

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

phi4:latest

Speed
50/50
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

phi4:latest

Reasoning
18/20
Coding
19/20
Instruction
12/20
Structured
13/15
Math
7/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Weak Multilingual: Strong
View qwen3-4b-qwen3.6-p… details | View phi4:latest 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