Downloads · 30 days
57
15% of all-time downloads
WaveCut/DeepSeek-V4-Flash-0731-REAM96-111B-exp-DS4-GGUF
DeepSeek-V4-Flash-0731-REAM96-111B-exp-DS4-GGUF is a machine learning model from WaveCut. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as mit.
[!WARNING] Experimental — most likely broken (renamed to -exp on 2026-08-12). This variant was produced by the second cascade step (REAM160 → REAM128 → REAM96). Severe multi-turn degradation was observed: generation t…
Downloads · 30 days
57
15% of all-time downloads
All-time downloads
373
Public
Repo size
38 GB
Likes
0
Public
Click a slice to open those files.
.gguf37.8 GB · 100%
From the Hugging Face model README
[!WARNING] Experimental — most likely broken (renamed to
-expon 2026-08-12). This variant was produced by the second cascade step (REAM160 → REAM128 → REAM96). Severe multi-turn degradation was observed: generation typically collapses into gibberish from the second request onward. No quality evidence was ever collected for this release. Kept for archival reference only; do not use for inference. A rebuilt REAM96 (single-step prune from the base model, new calibration) will be published at the original repo idWaveCut/DeepSeek-V4-Flash-0731-REAM96-111B.
This single-file DS4 GGUF was produced directly from the committed REAM96 native checkpoint. It preserves the 43-layer, 96-routed-expert, one-shared-expert, top-k 6 topology.
Runtime requirement: this is a DS4-specific GGUF. Use the patched WaveCut DS4 fork with dynamic expert-count support. Generic llama.cpp and Transformers loading are not claimed.
6747e7718dd08f00b680d0c16231f2d59ec3747e.NATIVE_READY.json SHA-256: 1a0aef0c8d4f736516ec1268b08d3ad698bef16f8e0ee90739fc0a0032831527.20260811T072216Z.| Artifact | Bytes | SHA-256 |
|---|---|---|
DeepSeek-V4-Flash-0731-REAM96-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf | 37,802,704,768 | e063760f1be5c5f30997461acc769d76e71d6c2f292645f22d7de3a5d769659c |
ream96-imatrix.dat | 169,087,878 | 897b8fdccbeb8d273752b07d5f11084857babe900fbbe7f183c3905e594a6db9 |
The GGUF contains 1,328 tensors. Its quantization template is pinned to antirez/deepseek-v4-gguf@591165d69ad5d27cf826dcc2cf687549e966f893.
The native checkpoint is a training-free cascade from the committed REAM128 release. It reduces every routed MoE layer from 128 to 96 experts using 3,072 calibration samples of 512 tokens each: 20% code, 10% math, 35% agent/tool, and 35% Russian/Cyrillic. Fresh layerwise saliency statistics, groups, merged experts, router mappings, and activations were computed for REAM96.
The importance matrix in this repository was generated fresh from the committed REAM96 native checkpoint; the REAM128 iMatrix was not reused. DS4 consumed it in strict iMatrix mode. Conversion was direct from Safetensors to GGUF without an intermediate F16 checkpoint.
Build or install the patched DS4 fork at the pinned revision, then run:
./ds4 \
-m ./DeepSeek-V4-Flash-0731-REAM96-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-chat-v2-imatrix.gguf \
--nothink
Remove --nothink only when intentionally enabling thinking with a suitable completion budget. Add backend, offload, context, and memory options for the installed CUDA or Metal build. The 37,802,704,768-byte model file alone is about 35.21 GiB; actual runtime memory also includes metadata, buffers, KV cache, and backend overhead.
The integrity checks prove artifact identity; they are not a quality or performance result.
MIT License, following the source checkpoint.