← All models

DeepSeek V4 Flash (FP4)

reasoningMITtools

DeepSeek V4 Flash in its native FP4+FP8 mixed-precision build — 284B-parameter Mixture-of-Experts (~13B active per token) with 1M-token context, Compressed Sparse Attention, and configurable Non-think / Think-High / Think-Max reasoning modes. The FP4 weights run in ~156 GB on llama via the `nsparks` GGUF (the FP4-FP8 native mix the upstream was trained at), and as a 4-bit MLX directory on Apple Silicon. Frontier-tier on-device reasoning for workstations and Mac Studio-class hardware — needs ~200 GB of usable memory.

At a glance

Parameters
284B
Quantization
FP4-FP8
Context window
1000K tokens
Approx. size
156.1 GB
Engines
llama.cpp, MLX
License
MIT (open)
Version
v1.0.0 , released 2026-05-17
Family
deepseek

Tuning

Defaults a gezel client applies out of the box, from real evaluation runs against this exact quantization.

sampling.maxTokens
16384
reasoning.thinkingBudget
4096
reasoning.enableThinking
true

Model behaviors

Client-side behavior modules the catalog enables for this model (reasoning-tag handling, fabrication detection, prompt shaping).

Sources

llama.cpp (GGUF)
nsparks/DeepSeek-V4-Flash-FP4-FP8-GGUF · DeepSeek-V4-Flash-FP4-FP8-native.gguf · FP4-FP8
MLX
mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit
Upstream
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash
Manifest
View on GitHub

Tags