Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

qwen3.5-9b-mlx

LM-STUDIO MLX

qwen3_5 · 9B · 4bit

Marginal

Mar 11, 2026 · Apple M4

Global Score
59 vs 59
Hardware Fit
69 vs 65
Quality Score
54 vs 57

Hardware

qwen3.5:35b-a3b qwen3.5-9b-mlx
MachineMacBook ProMac mini
CPUApple M4 ProApple M4
Cores1410
RAM48 GB24 GB
GPUApple M4 ProApple M4
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b qwen3.5-9b-mlx
Tokens/sec30.514.3
First chunk333 ms24 ms
TTFT30.0 s13.4 s
Load time9.8 s13.3 s
Memory usage25.1 GB2.5 GB
Memory %52%10%

HW Fit Score Breakdown

qwen3.5:35b-a3b

Speed
45/50
TTFT
0/20
Memory
24/30

qwen3.5-9b-mlx

Speed
32/50
TTFT
3/20
Memory
30/30

Quality

qwen3.5:35b-a3b

Reasoning
18/20
Coding
1/20
Instruction
7/20
Structured
6/15
Math
13/15
Multilingual
9/10
Reasoning: Strong Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Strong Multilingual: Strong

qwen3.5-9b-mlx

Reasoning
10/20
Coding
17/20
Instruction
5/20
Structured
9/15
Math
11/15
Multilingual
5/10
Reasoning: Weak Coding: Strong Instruction Following: Weak Structured Output: Adequate Math: Adequate Multilingual: Adequate
View qwen3.5:35b-a3b details | View qwen3.5-9b-mlx 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