You can deploy this model and start earning money today!

MimiTechAI/
dsv4-flash-0731-iq2xxs-gguf

Name: dsv4-flash-0731-iq2xxs-gguf
Availability: InStock

gguf

deepseek-ai/DeepSeek-V4-Flash-0731

Views

No views yet

DeepSeek-V4-Flash-0731 - IQ2XXS 2-bit GGUF

Quantized from the official deepseek-ai/DeepSeek-V4-Flash-0731 safetensors (48 shards, FP4/FP8) with the antirez/ds4 gguf-tools/deepseek4-quantize pipeline.

Recipe: IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8

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`

Size: 86.5 GB (1328 tensors)
Architecture: deepseek4, 43 layers, 256 routed experts (6 used), hash routing (3 layers), compressed KV + indexer, hyper-connections
Context: 1,048,576 tokens
Quantization: GGUF v3, imatrix: weight-energy fallback (V2 with activation imatrix planned)
tid2eid stored as I32 (ds4-engine compatible)

Usage

Runs 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

MimiTechAI/dsv4-flash-0731-iq2xxs-gguf

DeepSeek-V4-Flash-0731 - IQ2XXS 2-bit GGUF

Recipe: IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8

Usage

MimiTechAI/
dsv4-flash-0731-iq2xxs-gguf