Instructions to use primitive-ai/MiMo-V2.6-Flash-RL-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use primitive-ai/MiMo-V2.6-Flash-RL-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="primitive-ai/MiMo-V2.6-Flash-RL-NVFP4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("primitive-ai/MiMo-V2.6-Flash-RL-NVFP4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use primitive-ai/MiMo-V2.6-Flash-RL-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "primitive-ai/MiMo-V2.6-Flash-RL-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "primitive-ai/MiMo-V2.6-Flash-RL-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/primitive-ai/MiMo-V2.6-Flash-RL-NVFP4

SGLang

How to use primitive-ai/MiMo-V2.6-Flash-RL-NVFP4 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 "primitive-ai/MiMo-V2.6-Flash-RL-NVFP4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "primitive-ai/MiMo-V2.6-Flash-RL-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "primitive-ai/MiMo-V2.6-Flash-RL-NVFP4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "primitive-ai/MiMo-V2.6-Flash-RL-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use primitive-ai/MiMo-V2.6-Flash-RL-NVFP4 with Docker Model Runner:
```
docker model run hf.co/primitive-ai/MiMo-V2.6-Flash-RL-NVFP4
```

MiMo-V2.6-Flash-RL-NVFP4 / dflash /model.safetensors.index.json

jagat-primitive-org

weights: exact MXFP4 -> NVFP4 transcode of XiaomiMiMo/MiMo-V2.6-Flash-RL experts

af9b091 verified 9 days ago

Raw History Blame Contribute Delete

4.69 kB

	{
	"metadata": {
	"total_size": 2936114304
	},
	"weight_map": {
	"fc.weight": "dflash_draft_model.safetensors",
	"hidden_norm.weight": "dflash_draft_model.safetensors",
	"norm.weight": "dflash_draft_model.safetensors",
	"layers.0.input_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.0.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.mlp.up_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.mlp.down_proj.weight": "dflash_draft_model.safetensors",
	"layers.0.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
	"layers.1.input_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.1.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.mlp.up_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.mlp.down_proj.weight": "dflash_draft_model.safetensors",
	"layers.1.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
	"layers.2.input_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.2.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.mlp.up_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.mlp.down_proj.weight": "dflash_draft_model.safetensors",
	"layers.2.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
	"layers.3.input_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.3.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.mlp.up_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.mlp.down_proj.weight": "dflash_draft_model.safetensors",
	"layers.3.self_attn.attention_sink_bias": "dflash_draft_model.safetensors",
	"layers.4.input_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.4.post_attention_layernorm.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.q_norm.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.k_norm.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.q_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.k_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.v_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.o_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.mlp.gate_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.mlp.up_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.mlp.down_proj.weight": "dflash_draft_model.safetensors",
	"layers.4.self_attn.attention_sink_bias": "dflash_draft_model.safetensors"
	}
	}