qwen3.5-35b-a3b-t48-c8k:latest

qwen35moe · 36.0B · Q4_K_M

Dell Inc. PowerEdge R820 (Intel Xeon® E5-4650 v2)

256 GB · Microsoft Windows Server 2022 Datacenter 10.0.20348

Tested on September 6, 2026 · Submitted by Csaba_R820

Top 37% Compare

Global Score

81 /100

Not Rec.

Hardware Fit

63/100

Quality

88/100

Get this model

🦙

Ollama

ollama pull qwen3.5-35b-a3b-t48-c8k:latest

View on Ollama Library

ollama.com/library/qwen3.5-35b-a3b-t48-c8k

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Dell Inc. PowerEdge R820
CPU: Intel Xeon® E5-4650 v2
Cores: 80 threads (40 cores)
Frequency: 2.4 GHz
RAM: 256 GB DDR3
GPU: Microsoft Remote Display Adapter, NVIDIA Tesla P4, NVIDIA Tesla P4, Microsoft Basic Display Adapter
OS: Microsoft Windows Server 2022 Datacenter 10.0.20348
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 17.2
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.1
First chunk latency Delay before the first streamed chunk arrives from runtime: 845 ms
Time to first token How fast the model starts responding — lower is better: 845 ms
Load time Time to load the model into memory before inference: 103.1 s
Memory usage RAM consumed during inference — percentage of total system memory: 21.9 GB (9%)
Total tokens Total number of tokens generated across all benchmark prompts: 1101

Score breakdown

Speed

16/50

Time to first token

17/20

Memory

30/30

Quality

Reasoning

17/20

Coding

18/20

Instruction following

16/20

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 0.32.15
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 4a38a8e7404f6504bbc81c001c41be6a83ec0e5542cada1f69bb47514b962ba4

Interpretation

Hardware fit: 63/100. Overall suitability: NOT RECOMMENDED (Global 81/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Disqualifiers

Model load time too high: 103095ms (maximum: 90000ms for HIGH-END profile)

Bench Environment

CPU load: avg 59% (peak 71%)

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