DeepSeek R1 1.5B
by DeepSeek · deepseek-r1 family
1.5B
parameters
text-generation reasoning math
DeepSeek R1 1.5B is a distilled reasoning model based on Qwen 2.5, bringing chain-of-thought reasoning to ultra-lightweight hardware. Despite its tiny size, it shows the characteristic "thinking" behavior of the R1 family on math and logic tasks. At under 3 GB VRAM for Q8, it runs on virtually any hardware — great for edge devices, experimenting with reasoning models, or as a fast local assistant.
Quick Start with Ollama
ollama run 1.5b-q8_0 | Creator | DeepSeek |
| Parameters | 1.5B |
| Architecture | transformer-decoder |
| Context | 128K tokens |
| Released | Jan 20, 2025 |
| License | MIT |
| Ollama | deepseek-r1:1.5b |
Quantization Options
| Format | File Size | VRAM Required | Quality | Ollama Tag |
|---|---|---|---|---|
| Q4_K_M | 1.1 GB | 2 GB |
★
★
★
★
★
| 1.5b-q4_K_M |
| Q8_0 rec | 1.9 GB | 3 GB |
★
★
★
★
★
| 1.5b-q8_0 |
| F16 | 3.5 GB | 5 GB |
★
★
★
★
★
| 1.5b-fp16 |
Compatible Hardware
for Q8_0 (3 GB VRAM)
Compatible Hardware
| Hardware | VRAM | Type | Fit | Est. Speed |
|---|---|---|---|---|
| Mac Studio M4 Ultra 512GB | 512 GB | mac | Runs | ~273 tok/s |
| Mac Pro M2 Ultra 192GB | 192 GB | mac | Runs | ~267 tok/s |
| Mac Studio M4 Ultra 192GB | 192 GB | mac | Runs | ~273 tok/s |
| Mac Studio M4 Max 128GB | 128 GB | mac | Runs | ~182 tok/s |
| MacBook Pro M4 Max 128GB | 128 GB | mac | Runs | ~182 tok/s |
| MacBook Pro M3 Max 96GB | 96 GB | mac | Runs | ~133 tok/s |
| Mac mini M4 Pro 64GB | 64 GB | mac | Runs | ~91 tok/s |
| Mac Studio M4 Max 64GB | 64 GB | mac | Runs | ~182 tok/s |
| MacBook Pro M4 Max 64GB | 64 GB | mac | Runs | ~182 tok/s |
| Mac mini M4 Pro 48GB | 48 GB | mac | Runs | ~91 tok/s |
| MacBook Pro M3 Max 48GB | 48 GB | mac | Runs | ~133 tok/s |
| MacBook Pro M4 Max 48GB | 48 GB | mac | Runs | ~182 tok/s |
| MacBook Pro M4 Pro 48GB | 48 GB | mac | Runs | ~91 tok/s |
| Mac Studio M4 Max 36GB | 36 GB | mac | Runs | ~182 tok/s |
| MacBook Pro M3 Pro 36GB | 36 GB | mac | Runs | ~50 tok/s |
| NVIDIA GeForce RTX 5090 | 32 GB | gpu | Runs | ~597 tok/s |
| iMac M4 32GB | 32 GB | mac | Runs | ~40 tok/s |
| Mac mini M4 32GB | 32 GB | mac | Runs | ~40 tok/s |
| MacBook Air M4 32GB | 32 GB | mac | Runs | ~40 tok/s |
| AMD Radeon RX 7900 XTX | 24 GB | gpu | Runs | ~320 tok/s |
| NVIDIA GeForce RTX 3090 | 24 GB | gpu | Runs | ~312 tok/s |
| NVIDIA GeForce RTX 4090 | 24 GB | gpu | Runs | ~336 tok/s |
| iMac M3 24GB | 24 GB | mac | Runs | ~33 tok/s |
| Mac mini M2 24GB | 24 GB | mac | Runs | ~33 tok/s |
| Mac mini M4 Pro 24GB | 24 GB | mac | Runs | ~91 tok/s |
| MacBook Air M2 24GB | 24 GB | mac | Runs | ~33 tok/s |
| MacBook Air M4 24GB | 24 GB | mac | Runs | ~40 tok/s |
| MacBook Pro M4 Pro 24GB | 24 GB | mac | Runs | ~91 tok/s |
| AMD Radeon RX 7900 XT | 20 GB | gpu | Runs | ~267 tok/s |
| MacBook Pro M3 Pro 18GB | 18 GB | mac | Runs | ~50 tok/s |
| AMD Radeon RX 6800 XT | 16 GB | gpu | Runs | ~171 tok/s |
| AMD Radeon RX 7800 XT | 16 GB | gpu | Runs | ~208 tok/s |
| Intel Arc A770 | 16 GB | gpu | Runs | ~187 tok/s |
| NVIDIA GeForce RTX 4060 Ti 16GB | 16 GB | gpu | Runs | ~96 tok/s |
| NVIDIA GeForce RTX 4070 Ti Super | 16 GB | gpu | Runs | ~224 tok/s |
| NVIDIA GeForce RTX 4080 Super | 16 GB | gpu | Runs | ~245 tok/s |
| NVIDIA GeForce RTX 4080 | 16 GB | gpu | Runs | ~239 tok/s |
| NVIDIA GeForce RTX 5070 Ti | 16 GB | gpu | Runs | ~299 tok/s |
| NVIDIA GeForce RTX 5080 | 16 GB | gpu | Runs | ~320 tok/s |
| iMac M1 16GB | 16 GB | mac | Runs | ~23 tok/s |
| iMac M4 16GB | 16 GB | mac | Runs | ~40 tok/s |
| Mac mini M1 16GB | 16 GB | mac | Runs | ~23 tok/s |
| Mac mini M4 16GB | 16 GB | mac | Runs | ~40 tok/s |
| MacBook Air M2 16GB | 16 GB | mac | Runs | ~33 tok/s |
| MacBook Air M3 16GB | 16 GB | mac | Runs | ~33 tok/s |
| MacBook Air M4 16GB | 16 GB | mac | Runs | ~40 tok/s |
| MacBook Pro M1 16GB | 16 GB | mac | Runs | ~23 tok/s |
| MacBook Pro M2 Pro 16GB | 16 GB | mac | Runs | ~67 tok/s |
| AMD Radeon RX 7700 XT | 12 GB | gpu | Runs | ~144 tok/s |
| NVIDIA GeForce RTX 3060 12GB | 12 GB | gpu | Runs | ~120 tok/s |
| NVIDIA GeForce RTX 3080 12GB | 12 GB | gpu | Runs | ~304 tok/s |
| NVIDIA GeForce RTX 4070 Super | 12 GB | gpu | Runs | ~168 tok/s |
| NVIDIA GeForce RTX 4070 Ti | 12 GB | gpu | Runs | ~168 tok/s |
| NVIDIA GeForce RTX 4070 | 12 GB | gpu | Runs | ~168 tok/s |
| NVIDIA GeForce RTX 5070 | 12 GB | gpu | Runs | ~224 tok/s |
| NVIDIA GeForce RTX 2080 Ti | 11 GB | gpu | Runs | ~205 tok/s |
| NVIDIA GeForce RTX 3080 10GB | 10 GB | gpu | Runs | ~253 tok/s |
| AMD Radeon RX 7600 | 8 GB | gpu | Runs | ~96 tok/s |
| Intel Arc A750 | 8 GB | gpu | Runs | ~171 tok/s |
| NVIDIA GeForce RTX 3060 Ti | 8 GB | gpu | Runs | ~149 tok/s |
| NVIDIA GeForce RTX 3070 | 8 GB | gpu | Runs | ~149 tok/s |
| NVIDIA GeForce RTX 4060 Ti 8GB | 8 GB | gpu | Runs | ~96 tok/s |
| NVIDIA GeForce RTX 4060 | 8 GB | gpu | Runs | ~91 tok/s |
| MacBook Air M1 8GB | 8 GB | mac | Runs | ~23 tok/s |
| MacBook Air M2 8GB | 8 GB | mac | Runs | ~33 tok/s |
Benchmark Scores
52.0
mmlu