Entity · model
DeepSeek-V4-Flash
modelactive
deepseek-v4-flash-87628c9d·10 events·first seen Aliases: DeepSeek-V4-Flash, DeepSeek-V4-Flash-Base, DeepSeek-V4-Flash-DSpark, DeepSeek V4-Flash, DeepSeek V4 Flash 0731, DeepSeek-V4-Flash-0731
Co-occurring entities
More like this (12)
Recent events (10)
DeepSeek releases DeepSeek-V4-Flash-0731 on Hugging Face
DeepSeek has published DeepSeek-V4-Flash-0731, a new text-generation model on Hugging Face under the deepseek_v4 model family. The release is tagged as endpoints-compatible with fp8 and 8-bit quantization support, suggesting an efficiency-oriented variant of the V4 series. With 640 likes at release and zero downloads logged, this appears to be a freshly published checkpoint in the V4 Flash line.
Artificial Analysis publishes DeepSeek V4 Flash 0731 intelligence, performance, and price analysis
Artificial Analysis has published a benchmarking and pricing analysis of DeepSeek V4 Flash 0731, a new model variant from DeepSeek. The post is gaining significant traction on Hacker News with 343 points and 172 comments, suggesting notable community interest. The analysis covers intelligence benchmarks, performance metrics, and cost positioning for this flash-tier model.
DeepSeek-V4-Flash model update announced
DeepSeek has released an update to DeepSeek-V4-Flash, a faster/lighter variant of their flagship V4 model family. The announcement appeared in DeepSeek's official API documentation changelog. Community engagement on Hacker News (265 points, 112 comments) suggests meaningful practitioner interest in the update.
SLAI T-Rex: Full-parameter post-training of DeepSeek-V4 family on Ascend NPU SuperPOD achieves 34% MFU
Researchers present SLAI T-Rex, an end-to-end optimization framework for full-parameter post-training of trillion-parameter MoE models on Huawei Ascend NPU SuperPOD infrastructure, using the DeepSeek-V4 model family as the target workload. The system achieves 34.22% Model FLOPs Utilization, a 2.93x improvement over the open-source baseline, through hierarchical optimizations spanning model parallelism, communication orchestration, and kernel execution. Building on this infrastructure, the team develops a domain-specialized CPT and SFT pipeline for Operations Research tasks using DeepSeek-V4-Flash, producing a model that achieves 71.81% zero-shot Pass@1 on OR benchmarks, outperforming GPT-5.4-Mini by ~4 percentage points. The work is notable both as a non-GPU large-scale training system report and as a demonstration of domain specialization for complex mathematical reasoning.
DeepSeek releases DeepSeek-V4-Flash-DSpark on Hugging Face
DeepSeek has published a new model checkpoint, DeepSeek-V4-Flash-DSpark, on Hugging Face under the deepseek_v4 model family. The release is tagged as a text-generation model with FP8 and 8-bit support, suggesting an efficiency-optimized variant. The 'Flash' and 'DSpark' naming implies a faster or distilled derivative of the DeepSeek V4 flagship. Download counts are near zero, indicating a very recent upload.
Context-aware distillation and ablation study for Text2DSL Polkit rule generation
Researchers extend a Text2DSL system for generating Polkit domain-specific language rules from natural language, replacing prompt-only synthetic data generation with context-aware distillation using DeepSeek-V4-Flash as a teacher model operating under structured context (BNF grammar, API spec, closed vocabulary). The approach scales a verified corpus from 4,204 to 10,073 NL-to-Polkit-rule pairs at near-perfect validity rates. A factorial ablation across eight context conditions on GigaChat-10B-A1.8B finds that structured context is load-bearing rather than cosmetic, with vocabulary contributing the largest semantic-quality gains via Shapley decomposition.
DeepSeek releases DeepSeek-V4-Flash-Base on Hugging Face
DeepSeek has released DeepSeek-V4-Flash-Base, a new open-weights base model, on Hugging Face. The model uses FP8 precision and the deepseek_v4 architecture with safetensors format. Early traction is notable with over 66,000 downloads and 241 likes shortly after release, suggesting significant community interest in a 'Flash' variant of the V4 series.
DeepSeek releases DeepSeek-V4-Flash on Hugging Face
DeepSeek has released DeepSeek-V4-Flash, a new text-generation model published on Hugging Face under the deepseek-ai organization. The model supports FP8 and 8-bit quantization and is tagged as conversational and endpoints-compatible. With over 2.8 million downloads and 1,455 likes, it has seen substantial early uptake.
Goedel-Architect achieves state-of-the-art formal theorem proving with blueprint-based agentic framework
Goedel-Architect is an agentic framework for formal theorem proving in Lean 4 that uses blueprint generation — a dependency graph of definitions and lemmas — rather than recursive decomposition, enabling parallel lemma closure and global refinement. Built on DeepSeek-V4-Flash (284B-A13B), it achieves 99.2% pass@1 on MiniF2F-test and 75.6% on PutnamBench, scaling to 100% on MiniF2F, 88.8% on PutnamBench, and 4/6 on IMO 2025 when seeded with natural-language proofs. The authors claim state-of-the-art performance for an open-source pipeline at up to 500x lower cost than comparable systems.
DeepSeek V4 Preview Release: 1.6T-param Pro and 284B Flash Models with 1M Context, Open-Sourced
DeepSeek has released DeepSeek-V4 as an open-weights preview, comprising two MoE variants: V4-Pro (1.6T total / 49B active parameters) and V4-Flash (284B total / 13B active parameters). Both models support 1M token context by default, enabled by a novel Token-wise compression and DeepSeek Sparse Attention (DSA) architecture. V4-Pro claims open-source SOTA on agentic coding benchmarks and world-class math/STEM/coding performance rivaling top closed-source models, while V4-Flash offers near-parity reasoning at lower cost and latency. The API is live today with OpenAI and Anthropic compatibility, and legacy model endpoints will be retired in July 2026.