Back to leaderboard

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Good

Mar 5, 2026 · Intel Core™ i5-6500

Global Score
36 vs 61
Hardware Fit
100 vs 69
Quality Score
8 vs 58

Hardware

qwen36-distill-apex qwen3.5:4b
MachineMacBook ProGigabyte Technology Co., Ltd. H170M-D3H
CPUApple M5 MaxIntel Core™ i5-6500
Cores184
RAM64 GB16 GB
GPUApple M5 MaxGP104 [GeForce GTX 1070]
OSmacOS 27.0Ubuntu 24.04.4 LTS
Archarm64x64
Power Modebalancedlow-power

Performance

qwen36-distill-apex qwen3.5:4b
Tokens/sec55.235.7
First chunk210 ms438 ms
TTFT210 ms5.1 s
Load time4.8 s40.1 s
Memory usage0.9 GB5.5 GB
Memory %2%35%

HW Fit Score Breakdown

qwen36-distill-apex

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

qwen3.5:4b

Speed
50/50
TTFT
11/20
Memory
8/30

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

qwen3.5:4b

Reasoning
18/20
Coding
1/20
Instruction
8/20
Structured
8/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Adequate Math: Strong Multilingual: Strong
View qwen36-distill-apex details | View qwen3.5:4b 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