Measured model
Measured on a Mac Studio (M5 Max, 36GB)DeepSeek-R1-Distill-Qwen-1.5B
DeepSeek · Ollama name hf.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
On a Mac Studio (M5 Max, 36GB), DeepSeek-R1-Distill-Qwen-1.5B answers a simple question in about 1.7 s, gets 23% of the Japanese knowledge questions right, 27% of the math problems, and uses 1.5GB of memory.
Results
| Measure | Result | Among measured models | Note |
|---|---|---|---|
| Reply time | about 1.7 s | 13 of 34 | Until one simple common-sense question is answered (median of 50) |
| Knowledge (high school to university) | 23% | 34 of 34 | 200 questions, ±6, 61 cut off (counted wrong) |
| Math (word problems) | 27% | 34 of 34 | 100 questions, ±9, 23 cut off (counted wrong) |
| Memory used | 1.5GB | 2 of 34 | |
| EN→JA translation | 3 pts | 30 of 30 | out of 100 (chrF), about 2.1 s a sentence |
| JA→EN translation | 25 pts | 30 of 30 | out of 100 (chrF), about 1.5 s a sentence |
"Among measured models" is the place among the 34 models measured on this site (lower is better for time and memory).
Try it on your Mac
- Install the Mac version of Ollama from ollama.com and start it.
- Type this in Terminal. The first time, the model downloads; then you can chat with it.
ollama run hf.co/unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF:Q4_K_M
It used 1.5GB here. To use it comfortably alongside other apps, a Mac with 8GB of memory or more is a good guide (the model then takes about half the memory).
About the model
- Maker
- DeepSeek
- Size
- 1.78B parameters
- Quantization
- Q4_K_M
- Thinks before answering
- Yes
- Longest input at once
- 131,072 tokens
- Released (Hugging Face)
- Jan 20, 2025
- Generation speed
- 257.4 tok/s
- Start-up (loading)
- about 0.6 s
- Measured on
- Oct 6, 2026
- Ollama
- 0.34.3
- Hugging Face
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
- Series
- DeepSeek
What the parts of a name mean (size, quantization and so on): how to read a model name.
Models of similar memory
- LFM2.5-2.6B (2GB of memory, knowledge 73%, reply about 2.3 s)
- LFM2.5-1.2B-JP-202606 (1GB of memory, knowledge 51%, reply about 0.2 s)
- MiniCPM5-2B (2GB of memory, knowledge 73%, reply about 1.4 s)
- Ministral-3-3B-Instruct-2512 (3.2GB of memory, knowledge 47%, reply about 0.1 s)
- NVIDIA-Nemotron-3-Nano-4B-BF16 (3.3GB of memory, knowledge 72%, reply about 1.9 s)
Compare the main models on the text page. The series page lists every model measured.