Can I run DeepSeek R1 Distill Qwen 1.5B locally?
DeepSeek R1 Distill Qwen 1.5B by deepseek-ai has 1.8B parameters. At 4-bit with an 8K context it needs about 1.9 GB of GPU memory. It fits on 65 of 65 GPUs and Macs we track. See all models that fit in 8 GB of VRAM.
Memory needed by quant and context length
GB of GPU memory = weights + KV cache (FP16) + runtime overhead. Weights use real file sizes from unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF where available (marked •), otherwise parameter count × bits per weight. How we calculate.
| Quant | Quality | 4K ctx | 8K ctx | 32K ctx | 128K ctx |
|---|---|---|---|---|---|
| 2-bit (Q2_K) • | rough | 1.5 GB | 1.6 GB | 2.3 GB | 4.9 GB |
| 3-bit (Q3_K_M) • | usable | 1.7 GB | 1.8 GB | 2.4 GB | 5.1 GB |
| 4-bit (Q4_K_M) • | good, most popular | 1.8 GB | 1.9 GB | 2.6 GB | 5.2 GB |
| 5-bit (Q5_K_M) • | very good | 2.0 GB | 2.1 GB | 2.8 GB | 5.4 GB |
| 6-bit (Q6_K) • | near lossless | 2.2 GB | 2.3 GB | 2.9 GB | 5.6 GB |
| 8-bit (Q8_0) • | effectively lossless | 2.6 GB | 2.7 GB | 3.3 GB | 6.0 GB |
| 16-bit (F16/BF16) • | original weights | 4.1 GB | 4.2 GB | 4.9 GB | 7.5 GB |
Which GPUs and Macs run DeepSeek R1 Distill Qwen 1.5B?
Short answer with CPU offload and RAM needed: Can I run DeepSeek R1 on my PC?
Best quality quant that fits at 8K context. "Tight" = within 10% of usable memory. Speed is a ceiling from memory bandwidth (real speed is typically 50–80% of it).
| Hardware | Memory | Fits? | Best quant | Needs | Max tok/s (est.) | |
|---|---|---|---|---|---|---|
| RTX 3060 12GB | 12 GB | Fits | F16 | 4.2 GB | 101 | details |
| RTX 4060 Ti 16GB | 16 GB | Fits | F16 | 4.2 GB | 81 | details |
| RTX 3090 | 24 GB | Fits | F16 | 4.2 GB | 263 | details |
| RTX 4090 | 24 GB | Fits | F16 | 4.2 GB | 283 | details |
| RTX 5090 | 32 GB | Fits | F16 | 4.2 GB | 503 | details |
| RTX 5070 Ti | 16 GB | Fits | F16 | 4.2 GB | 252 | details |
| RX 7900 XTX | 24 GB | Fits | F16 | 4.2 GB | 270 | details |
| Mac M4 Pro 48GB | 48 GB | Fits | F16 | 4.2 GB | 77 | details |
| Mac M4 Max 128GB | 128 GB | Fits | F16 | 4.2 GB | 153 | details |
| Mac M3 Ultra 512GB | 512 GB | Fits | F16 | 4.2 GB | 230 | details |
| DGX Spark | 128 GB | Fits | F16 | 4.2 GB | 77 | details |
| RTX 4070 | 12 GB | Fits | F16 | 4.2 GB | 142 | details |
| RTX 5060 Ti 16GB | 16 GB | Fits | F16 | 4.2 GB | 126 | details |
| RTX 4060 | 8 GB | Fits | F16 | 4.2 GB | 76 | details |
| Arc B580 | 12 GB | Fits | F16 | 4.2 GB | 128 | details |
| RTX 3060 Ti | 8 GB | Fits | F16 | 4.2 GB | 126 | details |
| RTX 3070 | 8 GB | Fits | F16 | 4.2 GB | 126 | details |
| RTX 3080 10GB | 10 GB | Fits | F16 | 4.2 GB | 213 | details |
| RTX 3080 12GB | 12 GB | Fits | F16 | 4.2 GB | 256 | details |
| RTX 3090 Ti | 24 GB | Fits | F16 | 4.2 GB | 283 | details |
| RTX 4060 Ti 8GB | 8 GB | Fits | F16 | 4.2 GB | 81 | details |
| RTX 4070 Super | 12 GB | Fits | F16 | 4.2 GB | 142 | details |
| RTX 4070 Ti | 12 GB | Fits | F16 | 4.2 GB | 142 | details |
| RTX 4070 Ti Super | 16 GB | Fits | F16 | 4.2 GB | 189 | details |
| RTX 4080 | 16 GB | Fits | F16 | 4.2 GB | 201 | details |
| RTX 4080 Super | 16 GB | Fits | F16 | 4.2 GB | 207 | details |
| RTX 5060 | 8 GB | Fits | F16 | 4.2 GB | 126 | details |
| RTX 5070 | 12 GB | Fits | F16 | 4.2 GB | 189 | details |
| RTX 5080 | 16 GB | Fits | F16 | 4.2 GB | 270 | details |
| 2x RTX 3090 | 2×24 GB | Fits | F16 | 4.2 GB | 263 | details |
| 2x RTX 4090 | 2×24 GB | Fits | F16 | 4.2 GB | 283 | details |
| 2x RTX 5090 | 2×32 GB | Fits | F16 | 4.2 GB | 503 | details |
| RTX A6000 | 48 GB | Fits | F16 | 4.2 GB | 216 | details |
| RTX 6000 Ada | 48 GB | Fits | F16 | 4.2 GB | 270 | details |
| RTX PRO 6000 Blackwell | 96 GB | Fits | F16 | 4.2 GB | 503 | details |
| L40S | 48 GB | Fits | F16 | 4.2 GB | 243 | details |
| A100 40GB | 40 GB | Fits | F16 | 4.2 GB | 437 | details |
| A100 80GB | 80 GB | Fits | F16 | 4.2 GB | 573 | details |
| H100 PCIe | 80 GB | Fits | F16 | 4.2 GB | 562 | details |
| H100 SXM | 80 GB | Fits | F16 | 4.2 GB | 941 | details |
| H200 | 141 GB | Fits | F16 | 4.2 GB | 1348 | details |
| RX 7600 | 8 GB | Fits | F16 | 4.2 GB | 81 | details |
| RX 7700 XT | 12 GB | Fits | F16 | 4.2 GB | 121 | details |
| RX 7800 XT | 16 GB | Fits | F16 | 4.2 GB | 175 | details |
| RX 7900 GRE | 16 GB | Fits | F16 | 4.2 GB | 162 | details |
| RX 7900 XT | 20 GB | Fits | F16 | 4.2 GB | 225 | details |
| RX 9070 | 16 GB | Fits | F16 | 4.2 GB | 180 | details |
| RX 9070 XT | 16 GB | Fits | F16 | 4.2 GB | 180 | details |
| Ryzen AI Max+ 395 128GB | 128 GB | Fits | F16 | 4.2 GB | 72 | details |
| Arc A770 16GB | 16 GB | Fits | F16 | 4.2 GB | 157 | details |
| Mac M1 16GB | 16 GB | Fits | F16 | 4.2 GB | 19 | details |
| Mac M2 24GB | 24 GB | Fits | F16 | 4.2 GB | 28 | details |
| Mac M3 24GB | 24 GB | Fits | F16 | 4.2 GB | 28 | details |
| Mac M4 16GB | 16 GB | Fits | F16 | 4.2 GB | 34 | details |
| Mac M4 32GB | 32 GB | Fits | F16 | 4.2 GB | 34 | details |
| Mac M1 Pro 32GB | 32 GB | Fits | F16 | 4.2 GB | 56 | details |
| Mac M3 Pro 36GB | 36 GB | Fits | F16 | 4.2 GB | 42 | details |
| Mac M4 Pro 24GB | 24 GB | Fits | F16 | 4.2 GB | 77 | details |
| Mac M4 Pro 64GB | 64 GB | Fits | F16 | 4.2 GB | 77 | details |
| Mac M1 Max 64GB | 64 GB | Fits | F16 | 4.2 GB | 112 | details |
| Mac M2 Max 96GB | 96 GB | Fits | F16 | 4.2 GB | 112 | details |
| Mac M3 Max 128GB | 128 GB | Fits | F16 | 4.2 GB | 112 | details |
| Mac M4 Max 64GB | 64 GB | Fits | F16 | 4.2 GB | 153 | details |
| Mac M2 Ultra 192GB | 192 GB | Fits | F16 | 4.2 GB | 225 | details |
| Mac M3 Ultra 256GB | 256 GB | Fits | F16 | 4.2 GB | 230 | details |
Questions
How much VRAM does DeepSeek R1 Distill Qwen 1.5B need?
About 1.9 GB at 4-bit (Q4_K_M) with an 8K context: 1.0 GB of weights (real GGUF file size), 0.2 GB of KV cache and 0.7 GB of runtime overhead. At 8-bit it needs about 2.7 GB.
What is the smallest GPU that runs DeepSeek R1 Distill Qwen 1.5B?
At Q4_K_M and 8K context, the smallest single consumer GPU in our table that fits it is the RTX 4060 (8 GB).
Can I run DeepSeek R1 Distill Qwen 1.5B on a Mac?
Yes. At Q4_K_M with 8K context it fits on a Mac M1 16GB or larger, using the default macOS GPU memory limit.
Similar models
Same family or a similar parameter count, with the VRAM each needs at Q4_K_M and 8K context.
DeepSeek Coder 1.3B Instruct
1.3B · 2.8 GB at 4-bitDeepSeek OCR
3.3B · 2.9 GB at 4-bitDeepSeek VL2 Tiny
3.4B · 3.0 GB at 4-bitLFM3 1.7B
1.7B · 1.8 GB at 4-bitLFM3 1.7B Base
1.7B · 1.7 GB at 4-bitSmolLM2 1.7B Instruct
1.7B · 3.0 GB at 4-bitEmbed this
Free badge and "Will it run on my GPU?" widget for model cards, READMEs and blogs. No cookies, no tracking. All options.
Copy a snippet
Markdown badge
[](https://runsonmy.com/model/deepseek-r1-distill-qwen-1-5b/) Widget (script)
<div class="runsonmy-widget" data-model="deepseek-r1-distill-qwen-1-5b"><a href="https://runsonmy.com/model/deepseek-r1-distill-qwen-1-5b/">Will DeepSeek R1 Distill Qwen 1.5B run on my GPU? Check on RunsOnMy</a></div>
<script async src="https://runsonmy.com/embed.js"></script> Widget (iframe)
<iframe src="https://runsonmy.com/embed/m/deepseek-r1-distill-qwen-1-5b/" width="100%" height="220" style="max-width:440px;border:0" loading="lazy" title="Will DeepSeek R1 Distill Qwen 1.5B run on my GPU? (RunsOnMy)"></iframe> Model facts
| Hugging Face repo | deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B |
| Parameters | 1,777,088,000 (1.8B) |
| Layers / hidden size | 28 / 1536 |
| Attention | GQA; 12 heads, 2 KV heads, head dim 128 |
| KV cache per token (FP16) | 28.0 KiB |
| Max context | 131,072 tokens |
| License | mit |
| Released on HF | Jan 20, 2025 |
| Downloads (30d) / likes | 445,305 / 1,670 |
Sources: Hugging Face model API · config.json (deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) · GGUF files · GPU specs from vendor pages (list). Data fetched Nov 17, 2026. Spot an error? Report it.