hf.co/unsloth/Qwen3.8-27B-GGUF:UD-IQ2_XXS

OLLAMA GGUF

qwen35 · 27.3B · unknown

Not Rec.

Aug 22, 2026 · Apple M1 Pro

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

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K_M

Good

Apr 21, 2026 · Apple M2 Max

Global Score

31 vs 71

Hardware Fit

37 vs 92

Quality Score

28 vs 62

Hardware

hf.co/unsloth/Qwen… qwen3.5-35b-a3b-un…

MachineMacBook ProMac Studio

CPUApple M1 ProApple M2 Max

Cores1012

RAM16 GB96 GB

GPUApple M1 ProApple M2 Max

OSmacOS 26.6.2macOS 26.1

Archarm64arm64

Power Modebalancedbalanced

Performance

hf.co/unsloth/Qwen… qwen3.5-35b-a3b-un…

Tokens/sec5.459.8

First chunk5076 ms12 ms

TTFT5.1 s2.4 s

Load time0.3 sN/A

Memory usage11.6 GB29.7 GB

Memory %72%31%

HW Fit Score Breakdown

hf.co/unsloth/Qwen3.8-2…

Speed

13/50

TTFT

10/20

Memory

14/30

qwen3.5-35b-a3b-uncenso…

Speed

50/50

TTFT

12/20

Memory

30/30

Quality

hf.co/unsloth/Qwen3.8-2…

Reasoning

9/20

Coding

2/20

Instruction

1/20

Structured

1/15

Math

9/15

Multilingual

6/10

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

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

View hf.co/unsloth/Qwen… details | View qwen3.5-35b-a3b-un… 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