Back to leaderboard

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

LM-STUDIO GGUF

qwen3 · 4B · Q4_1

Good

Apr 21, 2026 · Apple M2 Max

hf.co/bartowski/ai9stars_G9v3-3B-GGUF:BF16

OLLAMA GGUF

llama · 2.99B · BF16

Good

Aug 23, 2026 · Apple M1 Pro

Global Score
65 vs 64
Hardware Fit
96 vs 92
Quality Score
51 vs 52

Hardware

qwen3-4b-qwen3.6-p… hf.co/bartowski/ai…
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M1 Pro
Cores1210
RAM96 GB16 GB
GPUApple M2 MaxApple M1 Pro
OSmacOS 26.1macOS 26.6.2
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-4b-qwen3.6-p… hf.co/bartowski/ai…
Tokens/sec99.629.9
First chunk18 ms100 ms
TTFT1.6 s100 ms
Load time4.8 s3.4 s
Memory usage0.3 GB8.9 GB
Memory %0%56%

HW Fit Score Breakdown

qwen3-4b-qwen3.6-plus-r…

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

hf.co/bartowski/ai9star…

Speed
50/50
TTFT
20/20
Memory
22/30

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

hf.co/bartowski/ai9star…

Reasoning
17/20
Coding
14/20
Instruction
6/20
Structured
0/15
Math
14/15
Multilingual
1/10
Reasoning: Strong Coding: Adequate Instruction Following: Weak Structured Output: Poor Math: Strong Multilingual: Poor

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