qwen3.5:35b

qwen35moe · 36.0B · Q4_K_M

ASUS (Intel Core™ i5-14600KF)

32 GB · Microsoft Windows 11 Famille 10.0.26200

Tested on March 7, 2026 · Submitted by RzoFlo

Top 24% Compare

Global Score

77 /100

Good

Hardware Fit

53/100

Quality

87/100

Get this model

🦙

Ollama

ollama pull qwen3.5:35b

View on Ollama Library

ollama.com/library/qwen3.5

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: ASUS
CPU: Intel Core™ i5-14600KF
Cores: 20 total (20 perf)
Frequency: 3.5 GHz
RAM: 32 GB DDR5
GPU: NVIDIA GeForce RTX 4070 Ti SUPER
OS: Microsoft Windows 11 Famille 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 16.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 719 ms
Time to first token How fast the model starts responding — lower is better: 719 ms
Load time Time to load the model into memory before inference: 17.8 s
Memory usage RAM consumed during inference — percentage of total system memory: 25.0 GB (79%)
Total tokens Total number of tokens generated across all benchmark prompts: 1094

Score breakdown

Speed

23/50

Time to first token

20/20

Memory

10/30

Quality

Reasoning

17/20

Coding

18/20

Instruction following

15/20

Structured output

15/15

Math

12/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.17.7
Model format: GGUF
Hardware profile: BALANCED
Result hash: c8f085ce293bb8a051d89b2aa4eb984085a581e3928145f0b7b5d82a8c83336a

Interpretation

Hardware fit: 53/100. Overall suitability: GOOD (Global 77/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Warnings

Significant swap activity during benchmark (+0.7 GB). Model may exceed available RAM — results are severely degraded.

Bench Environment

Swap delta: +0.7 GB CPU load: avg 23% (peak 30%)

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