Can you run it?
This page is a projection of the one entry record, the Reliability and Data control factors that Implement covers. The full verdict is set by all four factors together, floor-weighted so the weakest caps the whole.
- AssessUse & modify + Transparency
- ImplementData control + Reliability
- UseReliability
- SupportTransparency
Install & run
Download the safetensors from the verified deepseek-ai organisation on Hugging Face and
serve with Ollama, llama.cpp, vLLM or SGLang. The 8B runs on a single consumer GPU. Pin the
exact revision and verify checksums. The weight licence is the Llama Community Licence.
Hardware & VRAM requirements
The 8B runs on a single consumer GPU. The 70B runs on a single data-centre GPU, or on high-end consumer hardware when quantized. Context is 128K. The Llama base gives the broadest hardware and toolchain support of any distil base.
Serving stacks
vLLM, SGLang, llama.cpp and Ollama all support these models first-class. The Llama base has the widest toolchain coverage in the ecosystem.
Safe-deployment controls & Deployment Ceiling
Deployment Ceiling: T2 (conditional). Honour the Llama Community Licence first: the Acceptable Use Policy, the 700M-MAU clause and the "Built with Llama" naming and attribution are binding conditions.
Supply your own input/output guardrails and a guard model, because the models have no safety tuning of their own. Add prompt-injection defences and treat retrieved and tool content as untrusted in agentic use. Account for the China-aligned filtering carried over from R1.
Available quantizations
The models are extensively quantized (GGUF and lower-bit) via the Llama ecosystem. Redistribution of these derivatives must carry the Llama licence and AUP. Verify provenance per mirror.
Fine-tuning & adaptation
Fine-tuning and derivatives are permitted and carry the Llama restrictions (AUP, 700M-MAU and "Llama" naming and attribution). The distillation data and code are closed, so the distillation cannot be reproduced from scratch.
API / OpenAI-compatible integration
Serve behind an OpenAI-compatible endpoint (vLLM, SGLang or Ollama) and point the client at it. Handle the reasoning / think-tag output format at the client.
How this scores
The ownership factors this domain covers, drawn from the one entry record.
ReliabilityIs it reliable and good enough for the job?
StrongPerformance 3, operational 5 and safety 3: solid reasoning for the size and the broadest serving support of the distils. All three scores are at or above 3 and operational is 5, so reliability is strong. The gap is the absence of own safety tuning or a first-party guard model.
Doesn't extract your dataDoes running it keep your knowledge and data yours?
StrongSelf-hosted, the weights run entirely on the deployer's own infrastructure, on-device at 8B, with no telemetry and no claw-back. The licence restrictions limit use, not data residency.
Sources
The same evidence records as the entry sheet. Read means the text was verified; unverified means it is known to exist but not yet read.