qwen3.8:latest

qwen35 · 27.3B · Q4_K_M

THINKING MODEL

System manufacturer (AMD Ryzen 9 5950X 16-Core Processor)

32 GB · Microsoft Windows 11 Pro 10.0.26300

Tested on October 2, 2026 · Submitted by Qwen3.8vsGemma4

Top 67% Compare

Global Score

68 /100

Good

Hardware Fit

22/100

Quality

88/100

Get this model

🦙

Ollama

ollama pull qwen3.8:latest

View on Ollama Library

ollama.com/library/qwen3.8

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: System manufacturer
CPU: AMD Ryzen 9 5950X 16-Core Processor
Cores: 32 total (32 perf)
Frequency: 3.4 GHz
RAM: 32 GB DDR4
GPU: NVIDIA GeForce RTX 3090
OS: Microsoft Windows 11 Pro 10.0.26300
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 10.0
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±0.3
First chunk latency Delay before the first streamed chunk arrives from runtime: 1.0 s
Time to first token How fast the model starts responding — lower is better: 14.3 s
Load time Time to load the model into memory before inference: 22.3 s
Memory usage RAM consumed during inference — percentage of total system memory: 26.2 GB (82%)
Total tokens Total number of tokens generated across all benchmark prompts: 1410
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~511

Score breakdown

Speed

12/50

Time to first token

1/20

Memory

9/30

Quality

Reasoning

19/20

Coding

19/20

Instruction following

10/20

Structured output

15/15

Math

15/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.35.0
Model format: GGUF
Hardware profile: HIGH-END
Result hash: 37bef8a97d6cf5b911b4961e3d23b234e264caeac80d0d39aa660befd23bbbaa

Interpretation

Hardware fit: 22/100. Overall suitability: GOOD (Global 68/100). Category profile: Reasoning: Strong, Coding: Strong, Instruction Following: Adequate, Structured Output: Strong, Math: Strong, Multilingual: Strong.

Bench Environment

Swap delta: +0.0 GB CPU load: avg 47% (peak 59%)

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