DeepSeek-R1-Distill 70B
DeepSeek-R1 distilled to Llama 70B base. Strong general reasoning.
Task Fit
Not marked for typed decisions in the current library.
Not marked for code agent in the current library.
Code generation, debugging, refactoring, and benchmark signal.
General writing, Q&A, and assistant use.
Document QA benefits from long context and instruction following.
Not marked for vision in the current library.
Not marked for image generation in the current library.
Not marked for video generation in the current library.
Not marked for voice in the current library.
Evidence level
How this is assessed →Memory and hardware-fit values are planning estimates unless a tested report is linked.
Variants and Quant Artifacts
Choose the artifact first; hardware fit follows from RAM, VRAM, format, and runtime.
| Quant | Format | Quality | Min RAM | Reco RAM | Runtime | Action |
|---|---|---|---|---|---|---|
| Q4_K_M | gguf | balanced | 48GB | 80GB | ollama, llama.cpp, lm-studio | Plan with this |
| Q5_K_M | gguf | balanced | 50GB | 80GB | ollama, llama.cpp, lm-studio | Plan with this |
| Q8_0 | gguf | high | 78GB | 80GB | ollama, llama.cpp, lm-studio | Plan with this |
Recommended Hardware
Lowest estimated 5-year cost that can run this model.
Plenty of fast-memory headroom for this model.
Highest local performance signal among compatible hardware.
Benchmarks
Sources and compatibility
Execution evidence
Run DeepSeek-R1-Distill 70B with a documented recipe
Recipes connect hardware, a model artifact, tools, settings, verification, and a reportable result.
No verified recipe is linked to this record yet.
Compatibility estimates remain available in the planner. A recipe appears here only after its exact stack and verification protocol are documented.
Similar Models
DeepSeek-R1 reasoning model distilled to 32B. Excellent at math & logic.
DeepSeek's efficient MoE coder. 16B total / 2.4B active.
DeepSeek V4.1 Flash is DeepSeek's MIT-licensed open-weight multimodal MoE for reasoning, coding, agents, and native image understanding. The complete checkpoint is approximately 763B parameters, including a 552B backbone; its Causal Encoder-Decoder architecture activates 8B parameters during input prefill and 16B during output decoding. CSA2 and FP4 KV caching reduce long-context cache cost. The model supports a 1M-token context window and is available through official FP8 weights, the DeepSeek API, and Ollama Cloud. It remains a data-center-class deployment despite the low active-parameter count.