Downloads · 30 days
39
10% of all-time downloads
MimiTechAI/dsv4-flash-0731-iq2xxs-gguf
dsv4-flash-0731-iq2xxs-gguf is a machine learning model from MimiTechAI. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Quantized from the official deepseek-ai/DeepSeek-V4-Flash-0731 safetensors (48 shards, FP4/FP8) with the antirez/ds4 gguf-tools/deepseek4-quantize pipeline.
Downloads · 30 days
39
10% of all-time downloads
All-time downloads
400
Public
Repo size
86.6 GB
Likes
1
Trending 1
Click a slice to open those files.
.gguf86.6 GB · 100%
From the Hugging Face model README
Quantized from the official deepseek-ai/DeepSeek-V4-Flash-0731 safetensors (48 shards, FP4/FP8) with the antirez/ds4 gguf-tools/deepseek4-quantize pipeline.
| Tensor family | Type |
|---|---|
| Routed experts (gate/up) | iq2_xxs |
| Routed experts (down) | q2_K |
| Attention projections | q8_0 |
| Shared experts | q8_0 |
| Output head | q8_0 |
| Token embeddings | f16 |
| Compressor / Indexer / Hyper-connections | f16 |
deepseek4, 43 layers, 256 routed experts (6 used), hash routing (3 layers), compressed KV + indexer, hyper-connectionsRuns with the ds4 engine (antirez/ds4, supports DeepSeek-V4-Flash-0731):
./ds4 -m DeepSeek-V4-Flash-0731-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8.gguf --ctx 32768
Combine with DeepSeek-V4-Flash-0731-DSpark-support.gguf (sm54) for DSpark speculative decoding:
./ds4 -m ... -mtp DeepSeek-V4-Flash-0731-DSpark-support.gguf --dspark
See the source model repo for tokenizer/config: https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731