Downloads · 30 days
32
4% of all-time downloads
scouzi1966/DeepSeek-V4-Flash-0731-DwarfStar-GGUF
DeepSeek-V4-Flash-0731-DwarfStar-GGUF is a text generation model from scouzi1966. 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.
[!WARNING] Experimental AFM artifact. This repository is intended for a later version of maclocal-api that is still in development and has not yet been released. This is an AFM/DwarfStar deployment artifact, not a gen…
Downloads · 30 days
32
4% of all-time downloads
All-time downloads
730
Public
Repo size
162 GB
Likes
0
Public
Click a slice to open those files.
.gguf162 GB · 100%
From the Hugging Face model README
[!WARNING] Experimental AFM artifact. This repository is intended for a later version of maclocal-api that is still in development and has not yet been released. This is an AFM/DwarfStar deployment artifact, not a general-purpose GGUF release. It may not work with current public releases or other runtimes, and its behavior, quality, performance, memory use, compatibility, or file layout may change. For stable general-purpose MLX models, use mlx-community instead.
AFM project website: maclocal.ai
This repository packages the tested DwarfStar-compatible DeepSeek V4 Flash 0731 artifacts used by AFM. It provides one unambiguous main model and its optional DSpark speculative-decoding companion.
The GGUF conversion and quantization were created by Antirez for the DwarfStar engine. These files are mirrored from antirez/deepseek-v4-gguf for a simpler AFM installation workflow. This repository does not claim a new conversion or quantization.
| File | Purpose | Approximate size |
|---|---|---|
DeepSeek-V4-Flash-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-mxfp4-0731.gguf | Main DwarfStar model | 156 GB |
DeepSeek-V4-Flash-DSpark-support-0731.gguf | Optional DSpark companion | 6 GB |
Install the Hugging Face CLI:
curl -LsSf https://hf.co/cli/install.sh | bash
Download the main model to a location with at least 170 GB free:
mkdir -p /Volumes/edata2/models/ds4
hf download \
scouzi1966/DeepSeek-V4-Flash-0731-DwarfStar-GGUF \
DeepSeek-V4-Flash-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-mxfp4-0731.gguf \
--local-dir /Volumes/edata2/models/ds4
Run AFM:
afm mlx \
-m /Volumes/edata2/models/ds4/DeepSeek-V4-Flash-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-mxfp4-0731.gguf \
-w
AFM reads the GGUF metadata and automatically selects DwarfStar. The
--mlx-runtime dwarfstar option is not required.
Download the companion:
hf download \
scouzi1966/DeepSeek-V4-Flash-0731-DwarfStar-GGUF \
DeepSeek-V4-Flash-DSpark-support-0731.gguf \
--local-dir /Volumes/edata2/models/ds4
Enable it explicitly for greedy speculative decoding:
afm mlx \
-m /Volumes/edata2/models/ds4/DeepSeek-V4-Flash-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-mxfp4-0731.gguf \
--dspark-support /Volumes/edata2/models/ds4/DeepSeek-V4-Flash-DSpark-support-0731.gguf \
--temperature 0 \
-w
DSpark performance depends on draft-token acceptance and may be slower for low-acceptance prompts. The default DwarfStar path remains the reference.
SHA-256 / Hugging Face LFS OIDs:
0e3a161b670f686128ec5f92a601dfde616a37bf5e7e48999fa2d32471b57ec6 DeepSeek-V4-Flash-MXFP4Experts-F16HC-F16Compressor-F16Indexer-Q8Attn-Q8Shared-Q8Out-chat-v2-mxfp4-0731.gguf
7e319924541db3f7a163ed7e11d7532a70d48228ab59d36cb81e1d4511885360 DeepSeek-V4-Flash-DSpark-support-0731.gguf
The model card of the source DwarfStar repository identifies the artifacts as MIT and notes that the base-model copyright remains with DeepSeek. Users are responsible for complying with the source model's terms.