DeepSeek R1 Distill Sizes Explained: 1.5B, 7B, 8B, 14B, 32B and 70B by VRAM
DeepSeek R1 distill sizes explained: what 1.5B to 70B are, Ollama download sizes, how long reasoning raises memory use, and which size fits 8GB to 48GB.
-
-
LLM Out of Memory Fix: A Local OOM Troubleshooting Checklist (Ollama and llama.cpp)
LLM out of memory fix for local models: check usage first, then cut context and parallelism, quantize the KV cache, and only then change model or hardware.
-
LLM Context Length VRAM: How the KV Cache Works, Formulas, Worked Examples and Fixes
LLM context length VRAM guide: the KV cache formula, worked examples for 7B to 70B models, f16 vs q8_0 vs q4_0 cache, Ollama defaults and out-of-memory fixes.
-
How Much VRAM Does an LLM Need? Parameters, Quantization and Context
How much VRAM does an LLM need? Use weights + KV cache + overhead to estimate from parameters, quantization and context, with quick tables for 8GB to 48GB.
