qwen3:1.7b

qwen3 · 2.0B · Q4_K_M

Apple M4

32 GB · macOS 26.3

Tested on March 1, 2026

Top 40% Compare

Global Score

70 /100

Good

Hardware Fit

87/100

Quality

59/100

Get this model

🦙

Ollama

ollama pull qwen3:1.7b

View on Ollama Library

ollama.com/library/qwen3

🤗

Find on HuggingFace

GGUF versions & quantizations

Hardware

CPU: Apple M4
Cores: 10 total (4 perf + 6 eff)
Frequency: 2.4 GHz
RAM: 32 GB LPDDR5
GPU: Apple M4
OS: macOS 26.3
Arch: arm64
Power Mode: balanced

Performance

Tokens/sec Tokens generated per second — higher is better: 37.9
Standard deviation Variation of speed across benchmark runs — lower means more consistent: ±4.5
Time to first token How fast the model starts responding — lower is better: 3.1 s
Load time Time to load the model into memory before inference: 1.2 s
Memory usage RAM consumed during inference — percentage of total system memory: 4.9 GB (15%)
Total tokens Total number of tokens generated across all benchmark prompts: 1416
Thinking tokens (est.) Estimated internal reasoning tokens — models with "thinking" generate more tokens: ~930

Score breakdown

Speed

40/40

Time to first token

17/30

Memory

30/30

Quality

Reasoning

16/20

Coding

0/20

Instruction following

13/20

Structured output

14/15

Math

6/15

Multilingual

10/10

Category levels

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

Metadata

Spec version: 0.1.0
Runtime: Ollama 0.17.4
Model format: GGUF
Hardware profile: BALANCED
Result hash: 1eec6be8698cc56c5df85143c5cccd262eb9cfa4d4e473d14d69711ad2714c30

Interpretation

Hardware fit: 87/100. Overall suitability: GOOD (Global 70/100). Category profile: Reasoning: Strong, Coding: Poor, Instruction Following: Adequate, Structured Output: Strong, Math: Weak, Multilingual: Strong.

Run yours now

npx metrillm@latest bench

Requires Node 20+ and Ollama running