Hikari07jp/DeepSeek-V4.1-1017-Ablitrated-testmodel
just landed · new, unvettedmodel
New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.
Image text to text model from Hikari07jp (HF pipeline tag; the card has no one-line description). Mixture-of-experts, 763B total (384 experts, 6 per token). Context: 1M tokens (config). License: mit. Vendor-reported: "Hidden size 5120, vocab 129,280, 384 routed experts (top-6) + 1 shared expert, MoE intermediate 2304."
- Vendor-reported: Hidden size 5120, vocab 129,280, 384 routed experts (top-6) + 1 shared expert, MoE intermediate 2304.
- Org
- Hikari07jp
- Released
- 2026-10-23
- Status
- just landed · new, unvetted
- License
- mit (permissive)
- Parameters
- 763.2B
- Architecture
- MoE · 384 experts, 6/token · DeepseekV41ForCausalLM
- Context
- 1,048,576 tokens
- Task
- image-text-to-text · vision
- Signal
- 6 HF likes · 94 downloads
Runs on
estimate from params; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.
- Q4 ~459.6 GB (estimated size): no listed device
- Q8 ~812.6 GB (estimated size): no listed device
- FP16 ~1528.1 GB (estimated size): no listed device
Links
First published here 2026-10-23 · updated 2026-10-23 · markdown · JSON