# DeepSeek-R1-Distill-Llama-70B (Q4_K_M)

> DeepSeek · 70.6B · q4_k_m

Canonical: https://gpuninja.com/models/deepseek-r1-distill-llama-70b-q4-k-m
Data as of: 2026-10-11T15:47:21Z
Path: Home › AI models
- Specs verified: 11 Oct 2026, 15:47 UTC

## Specifications

- Publisher: DeepSeek (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)
- Parameters: 70.6B (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)
- Quantization: q4_k_m (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)
- Minimum VRAM: 42.5 GB (Unverified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)
- Context length: 128K tokens (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)
- Modality: text (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)
- License: MIT (Verified · source huggingface.co · retrieved 11 Oct 2026, 15:42 UTC · checked 11 Oct 2026, 15:47 UTC)

## Graphics cards that can run it

Board, Chip, VRAM, TDP, Length, Slots, Price, Stock, VRAM headroom

No graphics cards recorded that can run this model.

## Benchmarks

No benchmark results recorded.

## Sources

- https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B — Publisher, Parameters, Modality, License; last verified 11 Oct 2026, 15:47 UTC
- https://huggingface.co/bartowski/DeepSeek-R1-Distill-Llama-70B-GGUF/blob/main/DeepSeek-R1-Distill-Llama-70B-Q4_K_M.gguf — Quantization, Minimum VRAM; last verified 11 Oct 2026, 15:47 UTC
- https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B/blob/main/config.json — Context length; last verified 11 Oct 2026, 15:47 UTC