qwen3.5:35b-a3b-q4_K_M

qwen35moe · 36.0B · Q4_K_M

THINKING MODEL

Micro-Star International Co., Ltd. MS-7D98 (Intel Core™ i9-14900K)

128 GB · Microsoft Windows 11 Pro 10.0.26200

Tested on July 30, 2026 · Submitted by CsabaOrca

Top 93% Compare

Global Score

35 /100

Not Rec.

Hardware Fit

45/100

Quality

30/100

Get this model

🦙

Ollama

ollama pull qwen3.5:35b-a3b-q4_K_M

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: Micro-Star International Co., Ltd. MS-7D98
CPU: Intel Core™ i9-14900K
Cores: 32 total (32 perf)
Frequency: 3.2 GHz
RAM: 128 GB DDR5
GPU: Intel(R) UHD Graphics 770, NVIDIA Quadro K4000
OS: Microsoft Windows 11 Pro 10.0.26200
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 16.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.0
First chunk latency Delay before the first streamed chunk arrives from runtime: 781 ms
Time to first token How fast the model starts responding — lower is better: 30.0 s
Load time Time to load the model into memory before inference: 19.9 s
Memory usage RAM consumed during inference — percentage of total system memory: 21.8 GB (17%)
Total tokens Total number of tokens generated across all benchmark prompts: 1429
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~761

Score breakdown

Speed

15/50

Time to first token

0/20

Memory

30/30

Quality

Reasoning

8/20

Coding

0/20

Instruction following

4/20

Structured output

3/15

Math

6/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.32.4
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 6675449ecae0139799398b1e544a153226fbf08fa194bfe52b4cb60dd8f37ba3

Interpretation

Hardware fit: 45/100. Overall suitability: NOT RECOMMENDED (Global 35/100). Category profile: Reasoning: Weak, Coding: Poor, Instruction Following: Poor, Structured Output: Poor, Math: Weak, Multilingual: Strong.

Disqualifiers

Time to first token too high: 30000ms (maximum: 10000ms for HIGH-END profile)

Bench Environment

Power: AC CPU load: avg 42% (peak 50%)

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