Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

qwen3:4b

OLLAMA GGUF

qwen3 · 4.0B · Q4_K_M

Not Rec.

Jun 26, 2026 · Cortex-A78AE

Global Score
59 vs 32
Hardware Fit
69 vs 98
Quality Score
54 vs 4

Hardware

qwen3.5:35b-a3b qwen3:4b
MachineMacBook ProNVIDIA NVIDIA Jetson Orin Nano Engineering Reference Developer Kit Super
CPUApple M4 ProCortex-A78AE
Cores146
RAM48 GB7 GB
GPUApple M4 ProIntegrated / Unknown
OSmacOS 26.3.1Ubuntu 22.04.5 LTS
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b qwen3:4b
Tokens/sec30.517.9
First chunk333 ms950 ms
TTFT30.0 s950 ms
Load time9.8 s9.7 s
Memory usage25.1 GB3.0 GB
Memory %52%40%

HW Fit Score Breakdown

qwen3.5:35b-a3b

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

qwen3:4b

Speed
50/50
TTFT
20/20
Memory
28/30

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

qwen3:4b

Reasoning
4/20
Coding
0/20
Instruction
0/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5:35b-a3b details | View qwen3:4b 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