Can I Run DeepSeek-OCR on 24 GB system RAM?
作者： Jakub Rusinowski · 最后更新： 2026年9月11日
Yes — comfortably
Yes, comfortably — DeepSeek-OCR 3B at Q8_0 needs about 4.8 GB of the 19.2 GB usable on 24 GB system RAM, leaving ~14.4 GB spare and running at ~57.1 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: medium · Recommended quantization: Q8_0 · Estimated speed: ~57.1 tok/s
See what else this hardware can run →
或在 Vast.ai 比较，低至 $0.35/小时 (typical low · varies)
作为亚马逊联盟成员，我们从符合条件的购买中获得收入。云 GPU 链接为推荐链接——我们可能获得佣金，您无需额外付费。
24 GB system RAM — what it gives a model
| Usable memory for models | 19.2 GB |
| Memory bandwidth | 90 GB/s |
DeepSeek-OCR on 24 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 19.2 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 7.6 GB | ✓ Yes | 8K | ~39.3 tok/s | 6 GB |
| Q8_0 | 4.8 GB | ✓ Yes | 8K | ~57.1 tok/s | 3.2 GB |
| Q6_K | 4.1 GB | ✓ Yes | 8K | ~64.8 tok/s | 2.5 GB |
| Q5_K_M | 3.8 GB | ✓ Yes | 8K | ~69 tok/s | 2.1 GB |
| Q4_K_M | 3.5 GB | ✓ Yes | 8K | ~73.5 tok/s | 1.8 GB |
| Q3_K_M | 2.9 GB | ✓ Yes | 8K | ~82.6 tok/s | 1.3 GB |
| Q2_K | 2.6 GB | ✓ Yes | 8K | ~88.7 tok/s | 1 GB |
What to watch out for
- This model does not publish its full attention configuration, so the KV-cache share of these figures is inferred from its parameter count rather than computed exactly.
- These figures assume CPU-only inference. Any discrete GPU, even an 8 GB one, will be several times faster for models that fit in its VRAM.
Recommended setup
llama.cpp (CPU build) or Ollama — both run without a GPU
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 19.2 GB of the 24 GB is treated as usable for model weights (80% — the rest is the OS and running applications).
- DDR5-5600 dual channel at 89.6 GB/s peak. CPU decode is assumed to sustain 35% of that peak, because CPU inference is not purely bandwidth-bound — it also spends real time in compute and thread synchronisation. This figure is an assumption, not a fitted constant: no CPU measurement is in the calibration set.
- CPU-only inference: no GPU is assumed. A GPU of any size will beat these figures substantially.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is inferred from the parameter count because this model does not publish its full attention configuration.
FAQ
Can I run DeepSeek-OCR on 24 GB system RAM?
Yes, comfortably — DeepSeek-OCR 3B at Q8_0 needs about 4.8 GB of the 19.2 GB usable on 24 GB system RAM, leaving ~14.4 GB spare and running at ~57.1 tok/s (estimated), with room for about 8,192 tokens of context.
Which quantization of DeepSeek-OCR should I use on 24 GB system RAM?
Q8_0 — it needs about 4.8 GB of the 19.2 GB available, downloads as roughly 3.2 GB, and runs at an estimated 57.1 tokens/sec with up to 8K of context.
What limits DeepSeek-OCR on 24 GB system RAM?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
llama.cpp (CPU build) or Ollama — both run without a GPU
Other RAM Capacities
Other Models on 24 GB system RAM
- DeepSeek R1 on 24 GB system RAM
- Devstral on 24 GB system RAM
- EXAONE 3.5 on 24 GB system RAM
- Falcon 3 on 24 GB system RAM
- Gemma 2 Family on 24 GB system RAM
DeepSeek-OCR on GPUs
- DeepSeek-OCR on NVIDIA GeForce RTX 5060 Ti 8GB
- DeepSeek-OCR on NVIDIA GeForce RTX 5060
- DeepSeek-OCR on NVIDIA GeForce RTX 4060
What This Model Is Good At
Model & Tools
← Can I Run It? | DeepSeek-OCR model page | Check your hardware