MODEL PROFILE

DeepSeek-V4-Flash-0731-bf16

PrimeIntellect · DeepSeek-V4-Flash-0731-bf16

A bfloat16 re-export of deepseek-ai/DeepSeek-V4-Flash-0731. The weights are the published ones, dequantized: the dense linears from fp8 (e4m3 with ue8m0 scales over 128x128 blocks) and the routed experts from MXFP4, both to plain bfloat16. 43 layers, 114 safetensors shards. The upstream `config.json` carries `quantization_config` and `expert_dtype = "fp4"`. An inference engine reading those fields allocates fp8 linear parameters and MXFP4 expert parameters, which bfloat16 weights cannot fill. The routed experts at least fail loudly, in vLLM's `_load_w13`, where the packed MXFP4 shape does not match. The fp8 linears fail silently: a bfloat16 tensor has the same shape as the fp8 parameter it is loaded into, so `copy_` casts it elementwise and no dequantization scale is ever applied. Serving bfloat16 weights therefore requires a checkpoint whose config carries neither field, which is what this repo is. There is no Jinja chat template, by upstream design. Use the bundled `encoding/` directory, which is copied verbatim from upstream and is the reference implementation for turning OpenAI-format messages into an input string and for parsing completions back.

Text generationlicense:mit
Context windowNot disclosed
Input → OutputText → Text
Model weightsNot verified
Profile updated2026/11/2 19:16:45
OVERVIEW

Model overview

A bfloat16 re-export of deepseek-ai/DeepSeek-V4-Flash-0731. The weights are the published ones, dequantized: the dense linears from fp8 (e4m3 with ue8m0 scales over 128x128 blocks) and the routed experts from MXFP4, both to plain bfloat16. 43 layers, 114 safetensors shards. The upstream `config.json` carries `quantization_config` and `expert_dtype = "fp4"`. An inference engine reading those fields allocates fp8 linear parameters and MXFP4 expert parameters, which bfloat16 weights cannot fill. The routed experts at least fail loudly, in vLLM's `_load_w13`, where the packed MXFP4 shape does not match. The fp8 linears fail silently: a bfloat16 tensor has the same shape as the fp8 parameter it is loaded into, so `copy_` casts it elementwise and no dequantization scale is ever applied. Serving bfloat16 weights therefore requires a checkpoint whose config carries neither field, which is what this repo is. There is no Jinja chat template, by upstream design. Use the bundled `encoding/` directory, which is copied verbatim from upstream and is the reference implementation for turning OpenAI-format messages into an input string and for parsing completions back.

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

许可证:mit。模型介绍与第三方评测均以原来源的具体版本和方法为准。