Back to leaderboard

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M4

qwen36-distill-apex

OLLAMA GGUF
Not Rec.

Jul 17, 2026 · Apple M5 Max

Global Score
48 vs 36
Hardware Fit
77 vs 100
Quality Score
35 vs 8

Hardware

qwen3.5:4b qwen36-distill-apex
MachineMac miniMacBook Pro
CPUApple M4Apple M5 Max
Cores1018
RAM16 GB64 GB
GPUApple M4Apple M5 Max
OSmacOS 26.3macOS 27.0
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:4b qwen36-distill-apex
Tokens/sec18.955.2
First chunk316 ms210 ms
TTFT13.0 s210 ms
Load time3.7 s4.8 s
Memory usage5.9 GB0.9 GB
Memory %37%2%

HW Fit Score Breakdown

qwen3.5:4b

Speed
43/50
TTFT
4/20
Memory
30/30

qwen36-distill-apex

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

Quality

qwen3.5:4b

Reasoning
10/20
Coding
1/20
Instruction
4/20
Structured
3/15
Math
8/15
Multilingual
9/10
Reasoning: Weak Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Adequate Multilingual: Strong

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
View qwen3.5:4b details | View qwen36-distill-apex 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