This repository contains three exploratory, physically compacted expert-retention tiers derived from unsloth/DeepSeek-V4-Flash-0731-GGUF UD-IQ1_S at revision 1290dcca3f84612f646fb546fb9e8433c1b339b0.

Each variant keeps all 256 experts in protected hash-routing layers 0–2. Learned router layers 3–42 retain the experts selected by their fixed REAP prune plan:

Variant	Experts retained per learned layer	Files	Total bytes
K224	224	3	73,741,680,224
K192	192	3	64,944,122,464
K160	160	3	56,146,564,704

Load a tier by selecting its first split, for example:

bash

llama-server \
  -m DeepSeek-V4-Flash-0731-REAP-K224-00001-of-00003.gguf \
  -c 262144 -b 2048 -ub 512 -np 1 \
  --kv-offload -fa on -ctk q8_0 -ctv q8_0 -ngl 999

The pinned llama.cpp basis is a1f96d4fc2c9e4101a6666a9d87f547e7e880df6. These GGUFs encode deepseek4.expert_count as a per-layer array and therefore require the supplied patches/llama-cpp-deepseek4-per-layer-experts.patch. The supplied DeepSeek3 tokenizer long-run fix is also recommended. The REAP runtime patch is included for reproducing profiling and runtime-mask experiments.

Verification status

All three compact writers completed with status=passed; their complete receipts and prune plans are published under receipts/ and prune-plans/.
K192 and K224 were actually loaded with 262,144-token context, Q8 K/V cache, Flash Attention, and full GPU offload on an RTX PRO 6000 Blackwell 96GB.
Observed process memory was 70,672 MiB for K192 and 79,006 MiB for K224.
K192 served real requests after load; K224 reached health: ok.
K160 has not yet received an equivalent real-load smoke in this publication.

This is an exploratory three-candidate publication requested before completion of the preregistered Pi/SWE-Lancer evaluation. It is not an RTX_EXPERIMENT_PASSED or formal HF publication acceptance result. Compact-vs- runtime-mask logit/output parity, final quality selection, A100 cold validation, and the formal agent evaluation remain pending. Do not treat smaller storage or VRAM as a demonstrated quality or speed improvement.

See SHA256SUMS for the public GGUF hashes. The original full model is not mirrored or replaced here.

ioworker0/DeepSeek-V4-Flash-0731-REAP

DeepSeek V4 Flash REAP — UD-IQ1_S three-tier GGUF

Verification status

ioworker0/
DeepSeek-V4-Flash-0731-REAP