Back to leaderboard

qwen3.6:35b-mlx

OLLAMA GGUF

nvfp4

Not Rec.

Jul 17, 2026 · Apple M5 Max

qwen3.5:4b

OLLAMA GGUF

qwen35 · 4.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M4

Global Score
80 vs 48
Hardware Fit
77 vs 77
Quality Score
81 vs 35

Hardware

qwen3.6:35b-mlx qwen3.5:4b
MachineMacBook ProMac mini
CPUApple M5 MaxApple M4
Cores1810
RAM48 GB16 GB
GPUApple M5 MaxApple M4
OSmacOS 26.5.2macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.6:35b-mlx qwen3.5:4b
Tokens/sec129.818.9
First chunk77 ms316 ms
TTFT30.0 s13.0 s
Load time1.8 s3.7 s
Memory usage19.7 GB5.9 GB
Memory %41%37%

HW Fit Score Breakdown

qwen3.6:35b-mlx

Speed
50/50
TTFT
0/20
Memory
27/30

qwen3.5:4b

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

Quality

qwen3.6:35b-mlx

Reasoning
19/20
Coding
9/20
Instruction
18/20
Structured
11/15
Math
14/15
Multilingual
10/10
Reasoning: Strong Coding: Weak Instruction Following: Strong Structured Output: Adequate Math: Strong Multilingual: Strong

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

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