Instructions to use deepseek-ai/DeepSeek-V4.1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-ai/DeepSeek-V4.1-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-V4.1-Flash")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-V4.1-Flash", device_map="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use deepseek-ai/DeepSeek-V4.1-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-ai/DeepSeek-V4.1-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-ai/DeepSeek-V4.1-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash

SGLang

How to use deepseek-ai/DeepSeek-V4.1-Flash 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 "deepseek-ai/DeepSeek-V4.1-Flash" \
    --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": "deepseek-ai/DeepSeek-V4.1-Flash",
		"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 "deepseek-ai/DeepSeek-V4.1-Flash" \
        --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": "deepseek-ai/DeepSeek-V4.1-Flash",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-ai/DeepSeek-V4.1-Flash with Docker Model Runner:
```
docker model run hf.co/deepseek-ai/DeepSeek-V4.1-Flash
```

SaylorTwift HF Staff commited on 3 days ago

Commit

464a257

verified ·

1 Parent(s): dba1be0

Add community evaluation results

Browse files

Adds .eval_results/DeepSeek-V4.1-Flash.yaml with results mapped to registered Hub benchmarks (GPQA-Diamond, HLE, HLE w/ tools, Terminal-Bench 2.1/3.0/4.0, DeepSWE v1.1), extracted from the model card's Instruct-model benchmark table.

Files changed (1) hide show

.eval_results/DeepSeek-V4.1-Flash.yaml +67 -0

.eval_results/DeepSeek-V4.1-Flash.yaml ADDED Viewed

	@@ -0,0 +1,67 @@

+- dataset:
+    id: Idavidrein/gpqa
+    task_id: diamond
+  value: 90.9
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 36.8
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 63.9
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+  notes: "With tools; harness not specified in the model card."
+- dataset:
+    id: harborframework/terminal-bench-2.1
+    task_id: terminalbench_2_1
+  value: 90.6
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+  notes: "DeepSeek Harness, Minimal mode, 1M-token context."
+- dataset:
+    id: harborframework/terminal-bench
+    task_id: terminalbench_3
+  value: 30.0
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+  notes: "DeepSeek Harness, Minimal mode, 1M-token context."
+- dataset:
+    id: harborframework/terminal-bench
+    task_id: terminalbench_4
+  value: 31.2
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+  notes: "DeepSeek Harness, Minimal mode, 1M-token context."
+- dataset:
+    id: datacurve/deep-swe
+    task_id: deep_swe
+  value: 74.2
+  date: "2026-09-10"
+  source:
+    url: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
+    name: "DeepSeek-V4.1-Flash model card"
+  notes: "Reported as 'DeepSWE v1.1'; official mini-swe-agent harness."