Back to leaderboard

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

Global Score
36 vs 83
Hardware Fit
100 vs 96
Quality Score
8 vs 78

Hardware

qwen36-distill-apex qwen3-vl:4b-instruct
MachineMacBook ProMac Studio
CPUApple M5 MaxApple M2 Max
Cores1812
RAM64 GB96 GB
GPUApple M5 MaxApple M2 Max
OSmacOS 27.0macOS 26.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen36-distill-apex qwen3-vl:4b-instruct
Tokens/sec55.291.2
First chunk210 ms150 ms
TTFT210 ms150 ms
Load time4.8 s5.3 s
Memory usage0.9 GB42.5 GB
Memory %2%44%

HW Fit Score Breakdown

qwen36-distill-apex

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

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

Quality

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

qwen3-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong
View qwen36-distill-apex details | View qwen3-vl:4b-instruct 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