Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

qwen3:14b

OLLAMA GGUF

qwen3 · 14.8B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score
59 vs 58
Hardware Fit
69 vs 82
Quality Score
54 vs 48

Hardware

qwen3.5:35b-a3b qwen3:14b
MachineMacBook ProMacBook Pro
CPUApple M4 ProApple M1 Max
Cores1410
RAM48 GB32 GB
GPUApple M4 ProApple M1 Max
OSmacOS 26.3.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b qwen3:14b
Tokens/sec30.524.4
First chunk333 ms294 ms
TTFT30.0 s7.9 s
Load time9.8 s3.7 s
Memory usage25.1 GB13.8 GB
Memory %52%43%

HW Fit Score Breakdown

qwen3.5:35b-a3b

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

qwen3:14b

Speed
47/50
TTFT
5/20
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

qwen3:14b

Reasoning
13/20
Coding
6/20
Instruction
10/20
Structured
9/15
Math
2/15
Multilingual
8/10
Reasoning: Adequate Coding: Weak Instruction Following: Adequate Structured Output: Adequate Math: Poor Multilingual: Strong
View qwen3.5:35b-a3b details | View qwen3:14b 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