Downloads · 30 days
0
DeepSeek-V4-Flash-DSpark-IQ2XXS
mrtib/DeepSeek-V4-Flash-DSpark-IQ2XXS
DeepSeek-V4-Flash-DSpark-IQ2XXS is a text generation model from mrtib. Use it when you need the model to write or continue text. The card lists the license as mit.
Rhesadox GGUF of DeepSeek-V4-Flash with the DSpark speculative draft, re-quantized with the rhesadox deepseek-convert tool:
Access
Public
Updated Aug 3, 2026
Repo size
97.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.part0048 GB · 49%
At a glance
- Task
- Text Generation
- License
- mit
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 3, 2026
- SHA
- cd23da42
Try a prompt
Base models
Model card
From the Hugging Face model README
DeepSeek-V4-Flash (DSpark) — IQ2_XXS + native MTP draft (GGUF)
Rhesadox GGUF of DeepSeek-V4-Flash with the DSpark speculative draft, re-quantized with the rhesadox deepseek-convert tool:
- Experts: IQ2_XXS (2-bit, imatrix-weighted) · down-projection: Q2_K · attention/projection/shared-experts/output: Q8_0
- MTP draft: native FP4 (DSpark, 3 layers, 256 experts/layer)
⚠️ Split into 3 parts (HF's 50 GB per-file limit). Rejoin before use:
cat DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-nativeMTP-chat-v2-imatrix.gguf.part00 \
DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-nativeMTP-chat-v2-imatrix.gguf.part01 \
DeepSeek-V4-Flash-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-nativeMTP-chat-v2-imatrix.gguf.part02 \
> model.gguf
Validated: main matches the official DeepSeek-V4-Flash API token oracle (golden 3/3 PASS); draft loads and passes SparkDrafter.init (diagnoseInit OK, 3 layers × 256 experts).
- Task
- Text Generation
- License
- mit
- Created
- Aug 2, 2026
- Updated
- Aug 3, 2026