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

qwen35moe · 35B · Q4_K_M

THINKING MODEL

Mac Studio (Apple M2 Max)

96 GB · macOS 26.1

Tested on April 21, 2026 · Submitted by Frank

Top 49% Compare

Global Score

71 /100

Good

Hardware Fit

92/100

Quality

62/100

Get this model

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

MLX versions & conversions

Hardware

Machine: Mac Studio
CPU: Apple M2 Max
Cores: 12 total (8 perf + 4 eff)
Frequency: 2.4 GHz
RAM: 96 GB LPDDR5
GPU: Apple M2 Max
OS: macOS 26.1
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 59.8
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.2
First chunk latency Delay before the first streamed chunk arrives from runtime: 5 ms
Time to first token How fast the model starts responding — lower is better: 2.4 s
Load time Time to load the model into memory before inference: 8.5 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.4 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 1734
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~597

Score breakdown

Speed

50/50

Time to first token

12/20

Memory

30/30

Quality

Reasoning

18/20

Coding

8/20

Instruction following

13/20

Structured output

6/15

Math

12/15

Multilingual

5/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: LM Studio 0.4.10+1
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 1918702a41e5326366cda705ddbf18f8bb99a8ccab2ccf2c8765e8c2164e6793

Interpretation

Hardware fit: 92/100. Overall suitability: GOOD (Global 71/100). Category profile: Reasoning: Strong, Coding: Weak, Instruction Following: Adequate, Structured Output: Weak, Math: Strong, Multilingual: Adequate.

Bench Environment

Power: AC CPU load: avg 5% (peak 7%)

Run yours now

$ npm install -g metrillm@latest

$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest