qwen3.5-35b-a3b-t24-c8k:latest

OLLAMA GGUF

qwen35moe · 36.0B · Q4_K_M

Not Rec.

Jul 30, 2026 · Intel Core™ i9-14900K

qwen3.8-27b-uncensored-hauhaucs-aggressive-mtp

LM-STUDIO GGUF

qwen35 · 27B

Excellent

Sep 20, 2026 · AMD Ryzen 7 5800X 8-Core Processor

Global Score

34 vs 81

Hardware Fit

45 vs 64

Quality Score

29 vs 88

Hardware

qwen3.5-35b-a3b-t2… qwen3.8-27b-uncens…

MachineMicro-Star International Co., Ltd. MS-7D98System manufacturer

CPUIntel Core™ i9-14900KAMD Ryzen 7 5800X 8-Core Processor

Cores3216

RAM128 GB31 GB

GPUIntel(R) UHD Graphics 770, NVIDIA Quadro K4000Navi 44 [Radeon RX 9060 XT]

OSMicrosoft Windows 11 Pro 10.0.26200Ubuntu 26.04.1 LTS

Archx64x64

Power Modebalancedperformance

Performance

qwen3.5-35b-a3b-t2… qwen3.8-27b-uncens…

Tokens/sec16.511.7

First chunk772 ms50 ms

TTFT30.0 s1.1 s

Load time11.6 sN/A

Memory usage22.0 GB15.8 GB

Memory %17%51%

HW Fit Score Breakdown

qwen3.5-35b-a3b-t24-c8k…

Speed

15/50

TTFT

0/20

Memory

30/30

qwen3.8-27b-uncensored-…

Speed

19/50

TTFT

20/20

Memory

25/30

Quality

qwen3.5-35b-a3b-t24-c8k…

Reasoning

9/20

Coding

0/20

Instruction

4/20

Structured

1/15

Math

6/15

Multilingual

9/10

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

qwen3.8-27b-uncensored-…

Reasoning

17/20

Coding

19/20

Instruction

16/20

Structured

15/15

Math

11/15

Multilingual

10/10

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

View qwen3.5-35b-a3b-t2… details | View qwen3.8-27b-uncens… 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