DeepSeek-V3.2-NVFP4

Checkpointnvidia/DeepSeek-V3.2-NVFP4Broad indexModel card

Support summary

DeepSeek-V3.2-NVFP4 is a checkpoint. Official recipes or cookbooks cover vLLM and SGLang, without pinning a stable release.

Documented quantization
NVFP4
Documented features
Reasoning parsers, Tensor parallelism, and Tool calling

Hardware, quantization and features count only statements about this checkpoint; engine-wide capabilities are listed with each release.

Model notes and sources

Engine support

3 engines

Engine support for DeepSeek-V3.2-NVFP4
EngineReleaseCheckpoint supportEvidence scopeLast known supported
vLLMVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source: vllm · models/deepseek-ai/DeepSeek-V3.2.yamlReviewed
No supported release indexed
Features, dependencies and evidence for vLLM 0.28.0
SGLangVersion not pinnedRecipe / cookbookDocumented recipe

Official recipe

Source 1: sglang · docs/cookbook/autoregressive/DeepSeek/DeepSeek-V3_2.mdxSource 2: sglang · docs/src/snippets/autoregressive/deepseek-v32-deployment.jsxReviewed
No supported release indexed
Features, dependencies and evidence for SGLang 0.5.19
TensorRT-LLM1.2.1Newest indexedNo matching evidence curatedNo supported release indexed
Features, dependencies and evidence for TensorRT-LLM 1.2.1

Recipes and cookbooks