Tenzro
Language

DeepSeek V3 0324 (MoE)

DeepSeek V3 MoE — 685B total, 37B active, 128K context. Native Multi-Token-Prediction head (n=4, ~80% accept rate, ~1.8× decode speedup per DeepSeek tech report). Retired by upstream after 2026-07-24 in favor of DeepSeek V4.
MITSource verified
Specification
Model ID
deepseek-v3-0324
Family
deepseek
Modality
Language
Parameters
685B (MoE, 37B active)
Context
131,072 tokens
Quantization
Q4_K_M
Weights
351.9 GB
Minimum RAM
256 GB
Source

Weights and provenance.

Repository
unsloth/DeepSeek-V3-0324-GGUF
Registry license
MIT
Source license
mit
Access
Open — weights fetch without accepting additional terms.
Serve it
# Pull the weights onto a node
tenzro model download deepseek-v3-0324

# Serve it
tenzro model serve deepseek-v3-0324

# Or query the registry entry over JSON-RPC
curl https://rpc.tenzro.xyz \
  -X POST -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,
       "method":"tenzro_getModel",
       "params":[{"model_id":"deepseek-v3-0324"}]}'
Same family
DeepSeek V4 Flash (MoE)
284B (MoE, 13B active)
← All models