Back to leaderboard

qwen3.5:35b-a3b

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Mar 6, 2026 · Apple M4 Pro

microllm-50m:latest

OLLAMA GGUF

llama · 49.31M · F16

Not Rec.

Jun 28, 2026 · Apple M4 Pro

Global Score
59 vs 28
Hardware Fit
69 vs 80
Quality Score
54 vs 5

Hardware

qwen3.5:35b-a3b microllm-50m:latest
MachineMacBook ProMac mini
CPUApple M4 ProApple M4 Pro
Cores1412
RAM48 GB24 GB
GPUApple M4 ProApple M4 Pro
OSmacOS 26.3.1macOS 15.6.1
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3.5:35b-a3b microllm-50m:latest
Tokens/sec30.51000000.0
First chunk333 ms50 ms
TTFT30.0 s30.0 s
Load time9.8 s0.3 s
Memory usage25.1 GB0.1 GB
Memory %52%1%

HW Fit Score Breakdown

qwen3.5:35b-a3b

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

microllm-50m:latest

Speed
50/50
TTFT
0/20
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

microllm-50m:latest

Reasoning
0/20
Coding
0/20
Instruction
5/20
Structured
0/15
Math
0/15
Multilingual
0/10
Reasoning: Poor Coding: Poor Instruction Following: Weak Structured Output: Poor Math: Poor Multilingual: Poor
View qwen3.5:35b-a3b details | View microllm-50m:latest 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