DeepSeek-R1-Distill-Qwen-1.5B
- In Input modalities: Text Out Output modalities: Text
- Reasoning
- Open weights
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Details
- Tool use
- —
- Structured output
- —
- Family
- deepseek-r-distill-qwen
Not stated on DeepSeek’s pages: max input, reasoning efforts, reasoning can be off, max thinking budget, built-in tools, knowledge cutoff, aliases.
Run locally
Weights: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B- Parameters 1.8B
- Dense
- Native precision BF16
- Layers 28
- KV cache per token 28 KB
- Config positions 128K (config.json max_position_embeddings)
- API context 125K (maker’s API)
- Needs
- ≈ 4.0 GB (weights 3.3 (maker’s file) + KV cache 0.2 + overhead 0.5)
- Usable
- 21.6 GB (90% of its memory)
- Generation speed
- 133–200 tok/s
- Longest context
- 125K (the model’s limit)
- First token
- about 0.06–0.09 s for a 2K prompt
| Precision | Weights | Needs at 8K | On your hardware | Longest context |
|---|---|---|---|---|
| BF16 (native)maker’s file | 3.3 GB | ≈ 4.0 | ●Runs well 133–200 tok/s | 125K |
| Q8_0 | 1.8 GB | ≈ 2.5 | ●Runs well 237–356 tok/s | 125K |
| FP8 | 1.7 GB | ≈ 2.4 | ●Runs well 251–376 tok/s | 125K |
| Q6_K | 1.4 GB | ≈ 2.1 | ●Runs well 297–446 tok/s | 125K |
| Q5_K_M | 1.2 GB | ≈ 1.9 | ●Runs well 336–504 tok/s | 125K |
| Q5_0 | 1.1 GB | ≈ 1.9 | ●Runs well 346–519 tok/s | 125K |
| Q4_K_M | 1.0 GB | ≈ 1.7 | ●Runs well 383–575 tok/s | 125K |
| Q4_0 | 0.9 GB | ≈ 1.6 | ●Runs well 408–612 tok/s | 125K |
| IQ4_XS | 0.9 GB | ≈ 1.6 | ●Runs well 427–641 tok/s | 125K |
| Q3_K_Mquality drops | 0.8 GB | ≈ 1.5 | ●Runs well 457–685 tok/s | 125K |
| IQ3_XXSquality drops | 0.6 GB | ≈ 1.4 | ●Runs well 551–827 tok/s | 125K |
| Q2_Kquality drops | 0.6 GB | ≈ 1.3 | ●Runs well 559–839 tok/s | 125K |
| IQ2_XXSquality drops | 0.4 GB | ≈ 1.1 | ●Runs well 728–1092 tok/s | 125K |
Click a row to choose a precision. “Maker’s file” sizes are the maker’s own files; others are parameters × bits per weight.
Compared with other hardware
Each at the highest precision it runs. Click one for details.
Smallest that runs it (Q4_K_M, 8K): GPU GeForce RTX 3080; unified memory Apple M5 · 16 GB.
Run commands
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --max-model-len 8192
Memory to fine-tune
Batch 1, 2,048-token sequences, gradient checkpointing; LoRA and QLoRA train rank-16 adapters on the attention projections.
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by us- Epoch AI · GPQA Diamond 33.6%
#157 of 168 listed models · ±2.06
- Epoch AI · OTIS Mock AIME 2024–2025 21.4%
#124 of 159 listed models · ±5.28
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Nov 4, 2026
- changes we made
Changes
All changes →No changes recorded yet.
Sources
- Alibaba Cloud Model Studio: text generation models (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Sep 29, 2026
- deepseek-r1-distill-qwen-1.5b - Alibaba Cloud Model Studio (opens in a new tab) docs.modelstudio.console.alibabacloud.com · checked Sep 29, 2026
- 模型上下架與更新in Chinese (opens in a new tab) alibabacloud.com · checked Sep 29, 2026
- Release DeepSeek-R1 · deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B at 80da49e (opens in a new tab) huggingface.co · checked Oct 30, 2026
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B model card (opens in a new tab) huggingface.co · checked Oct 30, 2026
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B config.json (opens in a new tab) huggingface.co · checked Nov 5, 2026
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B files (opens in a new tab) huggingface.co · checked Oct 30, 2026
DeepSeek’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
DeepSeek · China · deepseek.com
Related models
Snapshots, the same family and other models from this provider