DE

DeepSeek R1 Distill Llama 70B lecore

DeepSeekGGUF by staccsUpdated 2026-10-29
Download on Hugging Face
Parameters70.6B
Context128K
Layers80
Architecturellama
Smallest quant27.2 GB
Quick answer

DeepSeek R1 Distill Llama 70B lecore needs about 45.7 GB of memory at Q4_K_M (a 42.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 27.2 GB to 42.5 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

DeepSeek R1 Distill Llama 70B lecore – a large‑context reasoning model

DeepSeek R1 Distill Llama 70B lecore is a 70.6B parameter model trained with large‑scale reinforcement learning. It supports chain‑of‑thought reasoning and tool use. The model is available in GGUF format for llama.cpp, Ollama and LM Studio.

Good at

  • Reasoning with chain‑of‑thought
  • Tool use and self‑verification
  • Large context of 131072 tokens

Limits

  • Requires >30GB VRAM for unknown quant
  • Requires >45GB VRAM for Q4_K_M quant
  • No vision support

Best for

  • Complex reasoning tasks
  • Code generation
  • Mathematical problem solving

Who it’s for. Researchers and developers needing a high‑capacity reasoning model for local deployment. The model is MIT licensed and can be run with llama.cpp or compatible runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—27.2 GB 30.4 GB
Too big Get file →
Q4_K_M42.5 GB 45.7 GB
Too big Get file →

For systems with 32GB VRAM, use the unknown quant file (27.19GB, ~30.4GB memory). For larger GPUs, the Q4_K_M quant (42.52GB, ~45.7GB memory) offers higher quality. Memory estimates are approximate.

What GPU do you need for DeepSeek R1 Distill Llama 70B lecore?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is the main file (27.2 GB file, about 30.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q4_K_M (42.5 GB file, about 45.7 GB in use).

Which DeepSeek R1 Distill Llama 70B lecore quant should you choose?

Q4_K_M is the usual starting point for DeepSeek R1 Distill Llama 70B lecore: it balances file size and quality well. Here it is a 42.5 GB file.

If memory is tight, the smallest file is the first one in the table at 27.2 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters70.6B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bystaccs
FamilyDeepSeek
Licensemit
Downloads (HF)608
Last updated2026-10-29

Frequently asked questions about DeepSeek R1 Distill Llama 70B lecore

How much VRAM does DeepSeek R1 Distill Llama 70B lecore need?

About 45.7 GB at Q4_K_M with an 8K context window. That is the 42.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run DeepSeek R1 Distill Llama 70B lecore on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 30.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of DeepSeek R1 Distill Llama 70B lecore GGUF?

It depends on the quant: file is 27.2 GB, Q4_K_M is 42.5 GB.

What context length does DeepSeek R1 Distill Llama 70B lecore support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.

Where can I download DeepSeek R1 Distill Llama 70B lecore GGUF?

The files are on Hugging Face in the staccs/DeepSeek-R1-Distill-Llama-70B-lecore-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does DeepSeek R1 Distill Llama 70B lecore use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8GB VRAM?

No. The smallest quant requires over 30GB VRAM, so 8GB is insufficient.

Does this model support vision?

No. The model has no vision capabilities.

What license is the model released under?

The model is released under the MIT license.

Other GGUFs of DeepSeek-R1-Distill-Llama-70B

Similar models

Browse all →

More from staccs

All by staccs →

More DeepSeek models

All DeepSeek →

Other large models

All large models →