Instructions to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B")
model = AutoModelForCausalLM.from_pretrained("WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B

SGLang

How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B with Docker Model Runner:
```
docker model run hf.co/WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B
```

DeepSeek V4 Flash 0731 REAM160-180B

This measured release reduces the 43-layer routed MoE from 256 to 160 experts while preserving top-k 6 routing. It contains approximately 180.445B logical parameters.

Lineage and precision

Source: deepseek-ai/DeepSeek-V4-Flash-0731@7872f01b1d1fe23eabc4c98b48bffcef5a386062.
Build code revision: 7d69b8490736789d47be25e6d7ccf5a8effefa16.
Routed expert weights: source-native E2M1 FP4, block 32, with E8M0 scales.
Attention projections and their scales remain in the source FP8 layout and are copied byte-for-byte where unchanged.
REAM weight accumulation is deterministic FP32; BF16 is transient compute, not the primary checkpoint format.
MTP and DSpark tensors and metadata are absent.
Checkpoint: 100,797,983,212 bytes; committed NATIVE_READY.json SHA-256 68fc46c987891e6e763611612262b8fae0cbd3de7de300efa169b5701bfaaaec.

REAM methodology

REAM160 is a calibration-guided, training-free expert merge: it does not apply gradient updates or add training examples to the checkpoint.

Calibration composition: 3,072 samples x 512 tokens.

Slice	Samples	Share	Pinned sources and focus
Code	614	20.0%	`sahil2801/CodeAlpaca-20k` and `bigcode/self-oss-instruct-sc2-exec-filter-50k`; instruction following and executable code
Math	307	10.0%	`openai/gsm8k` and `AI-MO/NuminaMath-CoT`; arithmetic and mathematical reasoning
Agent/tool	1,075	35.0%	`NousResearch/hermes-function-calling-v1`; function selection and structured tool calls
Russian/Cyrillic	1,076	35.0%	`ZeroAgency/ru-big-russian-dataset`; Russian and Cyrillic language coverage

A disjoint 512-sample heldout split was excluded from calibration.

At each layer, REAP saliency is the routed activation norm multiplied by router probability. The 160 highest-saliency source experts become centroids; the remaining source experts are assigned by their mean output and router-gate similarity, with group capacity 32. Each group is merged by saliency-weighted deterministic FP32 accumulation, router rows are remapped, and top-k 6 routing is preserved. Calibration therefore determines which source experts are retained and combined for the code, math, agent/tool, and Russian/Cyrillic workload mix; it is not fine-tuning.

Measured validation

Hardware: 4x NVIDIA L40 44 GB.
Wall time: 26.555 hours.
Supervisor-accounted merge/finalization RunPod cost: $73.92.
Comparative heldout NLL/PPL: not measured for this release.

Semantic suite: 100/100 cases passed; ru_dialogue=pass, code=pass, math=pass, agent_tool=pass, think=pass, no_think=pass.

Loading and runtime compatibility

The configuration and tokenizer can be inspected with Transformers without remote code:

from transformers import AutoConfig, AutoTokenizer

repo_id = "WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B"
config = AutoConfig.from_pretrained(repo_id, trust_remote_code=False)
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=False)
print(config.num_hidden_layers, config.n_routed_experts, config.num_experts_per_tok)

End-to-end generation was validated with the REAM160 native expert-parallel loader on the hardware reported above. Stock AutoModelForCausalLM, vLLM, and SGLang loading is not claimed for this packed E2M1/E8M0 checkpoint; a runtime must implement the 160-expert DeepSeek V4 layout and its native FP4/FP8 storage.

Limitations

MTP and DSpark are intentionally absent.
Comparative heldout NLL/PPL was not measured for this release.
Stock AutoModelForCausalLM, vLLM, and SGLang loading was not validated for the packed E2M1/E8M0 checkpoint.

Downloads last month: 15

Safetensors

Model size

180B params

Tensor type

BF16

F32

F8_E4M3

I64

Model tree for WaveCut/DeepSeek-V4-Flash-0731-REAM160-180B

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(127)

this model

Quantizations

2 models