qwen3-5-4b-q4-k-m

llama · 4B · Q4_K_M

Mac Pro (Intel Core™ i5-10400)

32 GB · macOS 26.5.1

Tested on July 9, 2026

Top 24% Compare

Global Score

83 /100

Excellent

Hardware Fit

100/100

Quality

76/100

Get this model

🦙

Ollama

ollama pull qwen3-5-4b-q4-k-m

View on Ollama Library

ollama.com/library/qwen3-5-4b-q4-k-m

Get it in LM Studio

Search and download models directly from the app

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

Machine: Mac Pro
CPU: Intel Core™ i5-10400
Cores: 12 total (12 perf)
Frequency: 2.9 GHz
RAM: 32 GB Empty
GPU: AMD Radeon RX 6700 XT
OS: macOS 26.5.1
Arch: x64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 62.7
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±1.8
First chunk latency Delay before the first streamed chunk arrives from runtime: 278 ms
Time to first token How fast the model starts responding — lower is better: 278 ms
Load time Time to load the model into memory before inference: 0.0 s
Memory usage RAM consumed during inference — percentage of total system memory: 0.0 GB (0%)
Total tokens Total number of tokens generated across all benchmark prompts: 2686

Score breakdown

Speed

50/50

Time to first token

20/20

Memory

30/30

Quality

Reasoning

14/20

Coding

15/20

Instruction following

15/20

Structured output

15/15

Math

8/15

Multilingual

9/10

Category levels

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

Metadata

Spec version: 0.2.1
Runtime: Ollama 0.5.18
Model format: GGUF
Hardware profile: BALANCED
Result hash: f1c665bc0a1be9ca25a6681baf354257accb201a03930024bfc0f09514dd2b3c

Interpretation

Hardware fit: 100/100. Overall suitability: EXCELLENT (Global 83/100). Category profile: Reasoning: Adequate, Coding: Strong, Instruction Following: Strong, Structured Output: Strong, Math: Adequate, Multilingual: Strong.

Bench Environment

Thermal: nominal Power: AC CPU load: avg 21% (peak 26%)

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