qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Apr 21, 2026 · Apple M2 Max

phi-1_5

LM-STUDIO GGUF

phi2 · Q8_0

Not Rec.

Mar 6, 2026 · Intel Core™ i5-5300U

Global Score

71 vs 28

Hardware Fit

92 vs 66

Quality Score

62 vs 11

Hardware

qwen3.5-35b-a3b-un… phi-1_5

MachineMac StudioLENOVO 20BUS00700

CPUApple M2 MaxIntel Core™ i5-5300U

Cores124

RAM96 GB16 GB

GPUApple M2 MaxIntel(R) HD Graphics 5500

OSmacOS 26.1Microsoft Windows 10 Professionnel 10.0.19045

Archarm64x64

Power Modebalancedbalanced

Performance

qwen3.5-35b-a3b-un… phi-1_5

Tokens/sec59.86.9

First chunk5 ms3040 ms

TTFT2.4 s3.0 s

Load time8.5 sN/A

Memory usage0.4 GB1.4 GB

Memory %0%9%

HW Fit Score Breakdown

qwen3.5-35b-a3b-uncenso…

Speed

50/50

TTFT

12/20

Memory

30/30

phi-1_5

Speed

24/50

TTFT

16/20

Memory

26/30

Quality

qwen3.5-35b-a3b-uncenso…

Reasoning

18/20

Coding

8/20

Instruction

13/20

Structured

6/15

Math

12/15

Multilingual

5/10

Reasoning: Strong Coding: Weak Instruction Following: Adequate Structured Output: Weak Math: Strong Multilingual: Adequate

phi-1_5

Reasoning

2/20

Coding

2/20

Instruction

3/20

Structured

0/15

Math

2/15

Multilingual

2/10

Reasoning: Poor Coding: Poor Instruction Following: Poor Structured Output: Poor Math: Poor Multilingual: Poor

View qwen3.5-35b-a3b-un… details | View phi-1_5 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