DeepSeek

R1 Distill 8B Llama

reasoning

8B

Parameters

4,6 Go

Q4_K_M file

≥ 6,1 Go

Recommended VRAM

131 072

Max context

Not measured yet

No card has run the TokenBench protocol on this model yet. The current protocol covers a selection of models; benchmarking any catalog model from the app is coming soon.

Measure my card →

Which cards should it fit on?

Cards on the site whose video memory covers the recommended 6,1 Go (file + 4,000-token context). An estimate, not a measurement. Click a card for the detailed estimate.

Technical sheet

Published
2025-01-20
Architecture
32 layers · 8 KV heads · dimension 128
Attention
Standard: every layer keeps the whole context in memory.
Context cache (f16)
≈ 125 MB per 1,000 tokens · 4,0 Go for 32,768 tokens
GGUF file
bartowski/DeepSeek-R1-Distill-Llama-8B-GGUF · DeepSeek-R1-Distill-Llama-8B-Q4_K_M.gguf Download (4,6 Go)

Public Hugging Face data (official config.json, GGUF repo). The context cache only counts full-attention layers.