Unverified50% confidenceFactExact time
DeepSeek-V3 has a total of 685B parameters, and even after Q4 quantization its size still exceeds 400GB.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe DeepSeek R1 7B version requires approximately 14 GB of storage at original FP16 precision, and only 4.7 GB after quantization.78% similarUnverifiedDeepSeek released the weights for the first vision version of V4, with a model scale of 305B (approximately 305 billion parameters).77% similarUnverifiedIn the DeepSeek V1 era, each incremental token required nearly 400 KB of KV cache, which dropped to 48 KB in V3.2.77% similarVerifiedUsing GGUF Q4 quantization as a baseline, a 7B model requires approximately 4–6 GB of VRAM, a 13B model requires approximately 8–10 GB, and a 70B model requires more than 40 GB or multi-GPU parallelism.77% similarVerifiedThe Qwen2.5:7B model is approximately 4 GB in size after Q4 quantization.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985470API
curl https://kongchang.com/api/v1/knowledge/claims/985470MCP
get_claim(id=985470)