Instructions to use drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid with Transformers:

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

pipe = pipeline("image-text-to-text", model="drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid

SGLang

How to use drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid 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 "drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid" \
    --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": "drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid",
		"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 "drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid" \
        --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": "drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid with Docker Model Runner:
```
docker model run hf.co/drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid
```

DeepSeek-V4.1-Flash TR3 Hybrid

Custom hybrid quant of deepseek-ai/DeepSeek-V4.1-Flash for 4× NVIDIA DGX Spark (GB10).

This is not a uniform 3.5 bpw Pollard EXL3 pack. It is a TR3 hybrid: most routed experts are EXL3 3.0 bpw, the 64 hardest experts per layer stay native MXFP4.

Bits per weight

Piece	Format	BPW
Routed tail	EXL3-TR3 K=3, codebook mcg	3.0
Routed keep-64 / layer	native MXFP4 (E2M1 + UE8M0/32)	4.25
Expert-weighted mix	64 keep + rest tail	≈3.22
Attention, shared expert, norms, embeddings	official FP8 / native	unchanged
Engram (shards 47–48)	official, hardlinked	unchanged (~203 GB)

Do not label this repo “3 bpw only.” The honest headline is 3.0 bpw EXL3-TR3 tail + 64 MXFP4 keeps/layer (~3.22 bpw MoE mix).

Disk: official 476 GB → this pack 410 GB (48 shards). Non-Engram 273 → 207 GB (~0.76×), matching 320/384 experts at 3/4.25 and 64/384 kept MXFP4.

Recipe

Source: deepseek-ai/DeepSeek-V4.1-Flash (552B backbone, 384 routed + 1 shared, top-6, moe_intermediate_size=2304, 1M context).
Keep: 64 experts/layer with the highest trellis round-trip error, left as MXFP4.
Tail: EXL3 K3 mcg, full expert matrices (2304 and 5120 are both % 128 == 0).
DSpark layers 37–39: 128 routed experts; still keep-64, so 64 tail on those layers.
Hessian: identity / q_fallback (Pass A does not fit 4×128 GB unified memory).
Smoke: identity-H mcg 5120×2304, nmse 1.74e-2.
Encoder: encode_dsv41_tr3.py wrapping the TR3 numeric core.

config.json field hybrid_tr3_tail: bits: 3.0, codebook: mcg, keep_mxfp4_per_layer: 64.

Credit

The hybrid quant method is brandonmusic’s TR3 recipe, first published as brandonmusic/GLM-5.2-NVFP4-TR3-Hybrid: keep the highest round-trip-error experts in native 4-bit, EXL3-TR3 K3 mcg on the tail, same numeric core (encode_tr3_v31.py). This checkpoint ports that method onto DeepSeek-V4.1-Flash. If you use these weights, credit brandonmusic for the hybrid quant.

Also:

DeepSeek-AI for the base model.
EXL3 trellis / mcg as used in that TR3 pipeline.

This pack is not bot-lab-21/DeepSeek-V4.1-Flash-EXL3-3.5bpw-Pollard (uniform ~3.51 bpw Pollard on all routed experts). Different method, different BPW mix.

Intended runtime (4× DGX Spark)

EXL3 GEMM requires N % 128 == 0. Uniform TP4 on 2304-wide experts is 2304/4 = 576 (illegal). Options that are legal:

Plugin expert-parallel: 96 full-width 2304 experts/rank (this lab’s hybrid path).
Uneven TP4 slice 512/640/640/512 (Tony / cuda-exl3 128-aligned split).
TP3: 2304/3 = 768 (legal); needs V4.1 TP3 patches (virtual heads 64→72, etc.).

License

MIT, same as the DeepSeek-V4.1-Flash release.

Downloads last month: 55

Safetensors

Model size

650B params

Tensor type

BF16

F32

F8_E4M3

F16

I16

Model tree for drowzeys/DeepSeek-V4.1-Flash-TR3-Hybrid

Base model

deepseek-ai/DeepSeek-V4.1-Flash

Quantized

(51)

this model