Downloads · 30 days
60
1% of all-time downloads
DeepSeek-V4-Flash-0731-antirez-ds4-GGUF
schlaflos/DeepSeek-V4-Flash-0731-antirez-ds4-GGUF
DeepSeek-V4-Flash-0731-antirez-ds4-GGUF is a text generation model from schlaflos. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as mit.
Status: the GGUF is still uploading. This card is published ahead of the weights.
All-time downloads
8K
Public
Repo size
104 GB
Likes
10
Public
Repo makeup
Click a slice to open those files.
.gguf104 GB · 100%
At a glance
- Task
- Text Generation
- Library
- gguf
- License
- mit
- Access
- Public
- Created
- Jul 31, 2026
- Updated
- Aug 1, 2026
- SHA
- c10897cd
Try a prompt
Base models
Model card
From the Hugging Face model README
DeepSeek V4 Flash 0731 — GGUF for ds4
Status: the GGUF is still uploading. This card is published ahead of the weights.
These quants target the DS4 inference engine, not llama.cpp. https://github.com/antirez/ds4
They use DS4's
deepseek4tensor layout and metadata. Compatibility with llama.cpp, Ollama or LM Studio is untested — do not assume it works. Conversely, llama.cpp-format quants of this model (MXFP4 experts, BF16 tensors) cannot be loaded by ds4: those types are not in DS4's tensor type set.
Built from the official DeepSeek-V4-Flash-0731 release, which supersedes the V4 Flash preview.
Files
| File | Size | Routed experts | Everything else |
|---|---|---|---|
DeepSeek-V4-Flash-0731-Layers37-42Q4KExperts-OtherExpertLayersIQ2XXSGateUp-Q2KDown-AProjQ8-SExpQ8-OutQ8-imatrix.gguf | 90.9 GiB | layers 0–36: IQ2_XXS (gate/up) + Q2_K (down); layers 37–42: Q4_K (all three) | Q8_0 attn proj / shared experts / output, F16 router + embed + indexer + compressor + HC, F32 norms / sinks / bias |
Sized for 128 GB Apple Silicon.
Quantization recipe
The filename is the spec.
| Tensor class | Quant | Count |
|---|---|---|
blk.{0..36}.ffn_{gate,up}_exps | IQ2_XXS | 74 |
blk.{0..36}.ffn_down_exps | Q2_K | 37 |
blk.{37..42}.ffn_{gate,up,down}_exps | Q4_K | 18 |
blk.*.attn_{q_a,q_b,kv,output_a,output_b} | Q8_0 | 215 |
blk.*.ffn_{gate,up,down}_shexp | Q8_0 | 129 |
output.weight | Q8_0 | 1 |
token_embd.weight, blk.*.ffn_gate_inp | F16 | |
blk.*.attn_compressor_*, indexer_*, hc_* | F16 / F32 | |
*_norm.weight, attn_sinks, exp_probs_b | F32 | |
blk.{0,1,2}.ffn_gate_tid2eid | I32 | 3 |
Routed experts are ~91% of the payload but each expert sees only a fraction of
tokens, so aggressive quantization there costs less average quality than the
same treatment of router, projections or shared experts. The last six layers
keep Q4_K because late-layer error affects output disproportionately.
Imatrix provenance
Quantized with antirez's published importance matrix
(DeepSeek-V4-Flash-chat-v2-routed-moe-ds4-1p5m.dat), which was collected on
the V4 Flash preview, not on 0731.
The architecture, tokenizer and routing structure are byte-identical between the two releases, so the statistics apply dimensionally and should transfer well — an imatrix records which input columns carry activation energy, not the weight values themselves. But this has not been measured across the release boundary. A 0731-native imatrix may improve on it.
Notes on the 0731 release
0731 bundles the DSpark speculative-decoding module (mtp.0/1/2) into the same
checkpoint, where the preview shipped it as a separate repository. A matching
DSpark support GGUF can be built with
deepseek4-quantize --dspark-support.
ds4's reasoning-effort prompt predates this release: --think max emits the
prefix DeepSeek now labels high, and the new max tier has no corresponding
string in the runtime. This affects prompt construction only, not the weights.
Usage
git clone https://github.com/antirez/ds4 && cd ds4 && make
hf download schlaflos/DeepSeek-V4-Flash-0731-antirez-ds4-GGUF \
DeepSeek-V4-Flash-0731-Layers37-42Q4KExperts-OtherExpertLayersIQ2XXSGateUp-Q2KDown-AProjQ8-SExpQ8-OutQ8-imatrix.gguf \
--local-dir gguf
ln -sfn "$PWD/gguf/DeepSeek-V4-Flash-0731-Layers37-42Q4KExperts-OtherExpertLayersIQ2XXSGateUp-Q2KDown-AProjQ8-SExpQ8-OutQ8-imatrix.gguf" ds4flash.gguf
./ds4 -p "Explain Redis streams in one paragraph."
License
MIT. Base model copyright DeepSeek; GGUFs redistributed under the base model's release terms.
- Task
- Text Generation
- Library
- gguf
- License
- mit
- Languages
- en
- Created
- Jul 31, 2026
- Updated
- Aug 1, 2026