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 August 23, 2026 · Submitted by Csaba_R820

Top 45% Compare

Global Score

78 /100

Not Rec.

Hardware Fit

51/100

Quality

89/100

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, 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: 7.1
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: 997 ms
Time to first token How fast the model starts responding — lower is better: 997 ms
Load time Time to load the model into memory before inference: 45.4 s
Memory usage RAM consumed during inference — percentage of total system memory: 21.6 GB (8%)
Total tokens Total number of tokens generated across all benchmark prompts: 1092

Score breakdown

Speed

6/50

Time to first token

15/20

Memory

30/30

Quality

Reasoning

16/20

Coding

19/20

Instruction following

17/20

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: f5ff19ae6c881eb3b89978aec4e353af3a0d9a84e353f98ebefc81b9c8fb8a82

Interpretation

Hardware fit: 51/100. Overall suitability: NOT RECOMMENDED (Global 78/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Disqualifiers

Token speed too low: 7.1 tok/s (minimum: 8 tok/s for HIGH-END profile)

Bench Environment

CPU load: avg 48% (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