Back to leaderboard

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

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

qwen3.5:latest

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Not Rec.

Mar 8, 2026 · Apple M4

Global Score
65 vs 34
Hardware Fit
96 vs 58
Quality Score
51 vs 23

Hardware

qwen3-4b-qwen3.6-p… qwen3.5:latest
MachineMac StudioMac mini
CPUApple M2 MaxApple M4
Cores1210
RAM96 GB16 GB
GPUApple M2 MaxApple M4
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… qwen3.5:latest
Tokens/sec99.613.3
First chunk18 ms438 ms
TTFT1.6 s19.8 s
Load time4.8 s0.2 s
Memory usage0.3 GB8.0 GB
Memory %0%50%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

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

qwen3.5:latest

Speed
32/50
TTFT
1/20
Memory
25/30

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

qwen3.5:latest

Reasoning
6/20
Coding
1/20
Instruction
3/20
Structured
0/15
Math
5/15
Multilingual
8/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Weak Multilingual: Strong

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