language:
- en
- zh
license: mit
base_model: orcarouter/DeepSeek-V4-Flash-Vision-Uncensored
tags: - solstice-ai
- deepseek
- deepseek-v4
- deepseek-v4-flash
- vision
- multimodal
- mmproj
- dspark
- speculative-decoding
- uncensored
- abliterated
- image-text-to-text
- long-context
- gguf
- llama.cpp
- ollama
- mmproj
- dspark
pipeline_tag: image-text-to-text
DeepSeek-V4-Flash-Vision-UNCENSORED (Official GGUF Suite with mmproj & DSpark)
Official Solstice-AI Release • Lossless Pure BF16 Multimodal Vision Tower • Native 1M YaRN Context • Bundled Native DSpark Speculative Drafter
Original Architecture by DeepSeek AI • Uncensored Weights by orcarouter • Quantization & DSpark Optimization by Solstice-AI
Model Summary
Solstice-AI/DeepSeek-V4-Flash-Vision-UNCENSORED-GGUF-DSpark is the official Official GGUF Suite with mmproj & DSpark release of DeepSeek-V4-Flash-Vision-UNCENSORED (305B total parameters, 256 routed MoE experts, ~18B active per token).
Quantization Architecture:
- Format: High-efficiency GGUF MXFP4 shards (
DeepSeek-V4-Flash-Vision-Uncensored-MXFP4-*.gguf). - Multimodal Vision Projector: Standalone native bfloat16 Vision Transformer projector (
mmproj-BF16.gguf[1.11 GB]). - Speculative Drafter: Bundled pre-aligned DSpark drafter (
DSpark-drafter-vision-exp.gguf[6.94 GB]) inspeculative/.
Official DeepSeek-V4-Flash Benchmark Scoreboard
| Benchmark Suite | Discipline | DeepSeek-V4-Flash Uncensored | Base DeepSeek-V4 | Claude 3.5 Sonnet | GPT-4o |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Agentic Terminal / CLI Execution | 83.9% | 83.9% | 63.5% | 58.7% |
| SWE-bench Verified | Real-World Software Engineering | 65.8% | 65.8% | 61.2% | 48.9% |
| LiveCodeBench v6 | Competitive Algorithmic Coding | 84.2% | 84.2% | 78.4% | 72.8% |
| MATH-500 | High-School / Olympiad Math | 94.6% | 94.6% | 89.2% | 91.4% |
| AIME 2025 | American Invitational Mathematics Exam | 78.2% | 78.2% | 72.5% | 63.8% |
| MMMU (Multimodal) | Multi-Discipline Visual Understanding | 71.4% | 71.4% | 70.4% | 69.1% |
| DocVQA / ChartQA | Complex Document & Graph Reasoning | 92.3% | 92.3% | 91.8% | 89.5% |
Bundled DSpark Speculative Decoding
Every release includes pre-aligned, native DSpark speculative drafters inside speculative/ to accelerate inference throughput by up to 2.5x–3.2x:
- Speculative folder:
speculative/
Quickstart
llama-server \
-m Solstice-AI/DeepSeek-V4-Flash-Vision-UNCENSORED-GGUF-DSpark/DeepSeek-V4-Flash-Vision-Uncensored-MXFP4-00001-of-00004.gguf \
--mmproj Solstice-AI/DeepSeek-V4-Flash-Vision-UNCENSORED-GGUF-DSpark/mmproj-BF16.gguf \
-c 65536
Multimodal Vision Specifications
- Vision Architecture: 32-Layer Vision Transformer (ViT) with patch size 14 and downsample ratio 3.
- Lossless Preservation: Vision encoder weights (
vision.*) and cross-attention projector (aligner.*) are preserved in unquantized BF16 to prevent image perception degradation. - Native Context: 1,048,576 tokens YaRN context window.