Instructions to use cs2764/Step-3.7-Flash_dq4-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cs2764/Step-3.7-Flash_dq4-mlx with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("cs2764/Step-3.7-Flash_dq4-mlx")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use cs2764/Step-3.7-Flash_dq4-mlx with Transformers:

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

pipe = pipeline("text-generation", model="cs2764/Step-3.7-Flash_dq4-mlx", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("cs2764/Step-3.7-Flash_dq4-mlx", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use cs2764/Step-3.7-Flash_dq4-mlx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cs2764/Step-3.7-Flash_dq4-mlx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cs2764/Step-3.7-Flash_dq4-mlx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cs2764/Step-3.7-Flash_dq4-mlx

SGLang

How to use cs2764/Step-3.7-Flash_dq4-mlx 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 "cs2764/Step-3.7-Flash_dq4-mlx" \
    --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": "cs2764/Step-3.7-Flash_dq4-mlx",
		"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 "cs2764/Step-3.7-Flash_dq4-mlx" \
        --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": "cs2764/Step-3.7-Flash_dq4-mlx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

How to use cs2764/Step-3.7-Flash_dq4-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "cs2764/Step-3.7-Flash_dq4-mlx"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "cs2764/Step-3.7-Flash_dq4-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cs2764/Step-3.7-Flash_dq4-mlx with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "cs2764/Step-3.7-Flash_dq4-mlx"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default cs2764/Step-3.7-Flash_dq4-mlx

Run Hermes

hermes

OpenClaw new

How to use cs2764/Step-3.7-Flash_dq4-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "cs2764/Step-3.7-Flash_dq4-mlx"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "cs2764/Step-3.7-Flash_dq4-mlx" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use cs2764/Step-3.7-Flash_dq4-mlx with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "cs2764/Step-3.7-Flash_dq4-mlx"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "cs2764/Step-3.7-Flash_dq4-mlx"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "cs2764/Step-3.7-Flash_dq4-mlx",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use cs2764/Step-3.7-Flash_dq4-mlx with Docker Model Runner:
```
docker model run hf.co/cs2764/Step-3.7-Flash_dq4-mlx
```

Step-3.7-Flash_dq4-mlx / README.md

cs2764

Add files using upload-large-folder tool

9967117 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.84 kB

	---
	tags:
	- mlx
	- transformers
	- quantization
	- dq4
	---

	# Step-3.7-Flash_dq4

	This model is a DQ4 quantized version of the original model `Step-3.7-Flash` (local model).
	It was quantized locally using the `mlx_lm` library.

	## Quantization Methodology (DQ4)

	This model was quantized using the dynamic DQ4 (4-bit / 5-bit / 6-bit / 8-bit mixed) approach, inspired by the methodology described in the [mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8](https://huggingface.co/mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8) repository.

	The weights are mixed based on MLX layers:
	- Expert layers (switch_mlp / experts / shared experts) are quantized to 4-bit.
	- Expert `down_proj` in the first 5 layers is kept at higher quality (6-bit).
	- Expert `down_proj` every 5th layer is medium quality (5-bit).
	- All other layers (e.g. attention, routers, normalization) remain at 8-bit to serve as the "8-bit brain".

	The table below is generated from the actual output `config.json`, so it reflects exactly what was quantized.

	## Per-layer quantization map

	- Group size: 64
	- Quantized weight matrices: 530
	- Bit distribution: 4-bit ×232, 5-bit ×16, 6-bit ×4, 8-bit ×278
	- Modules not listed below (attention projections, embeddings, `lm_head`, routers, norms, dense MLPs) are kept at 8-bit or full precision as the high-precision backbone.

	\| Module pattern \| Bits \| Count \|
	\|---\|---\|---\|
	\| `language_model.lm_head` \| 8-bit \| 1 \|
	\| `language_model.model.embed_tokens` \| 8-bit \| 1 \|
	\| `language_model.model.layers.{i}.mlp.down_proj` \| 8-bit \| 3 \|
	\| `language_model.model.layers.{i}.mlp.gate.gate` \| 8-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.gate_proj` \| 8-bit \| 3 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.down_proj` \| 4-bit \| 32 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.down_proj` \| 5-bit \| 8 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.down_proj` \| 6-bit \| 2 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.gate_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.up_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.down_proj` \| 4-bit \| 32 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.down_proj` \| 5-bit \| 8 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.down_proj` \| 6-bit \| 2 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.gate_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.up_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.up_proj` \| 8-bit \| 3 \|
	\| `language_model.model.layers.{i}.self_attn.g_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.k_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.o_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.q_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.v_proj` \| 8-bit \| 45 \|

	---
	tags:
	- mlx
	- transformers
	- quantization
	- dq4
	---

	# Step-3.7-Flash_dq4

	This model is a DQ4 quantized version of the original model `Step-3.7-Flash` (local model).
	It was quantized locally using the `mlx_lm` library.

	## Quantization Methodology (DQ4)

	This model was quantized using the dynamic DQ4 (4-bit / 5-bit / 6-bit / 8-bit mixed) approach, inspired by the methodology described in the [mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8](https://huggingface.co/mlx-community/Kimi-K2.5-mlx-DQ3_K_M-q8) repository.

	The weights are mixed based on MLX layers:
	- Expert layers (switch_mlp / experts / shared experts) are quantized to 4-bit.
	- Expert `down_proj` in the first 5 layers is kept at higher quality (6-bit).
	- Expert `down_proj` every 5th layer is medium quality (5-bit).
	- All other layers (e.g. attention, routers, normalization) remain at 8-bit to serve as the "8-bit brain".

	The table below is generated from the actual output `config.json`, so it reflects exactly what was quantized.

	## Per-layer quantization map

	- Group size: 64
	- Quantized weight matrices: 530
	- Bit distribution: 4-bit ×232, 5-bit ×16, 6-bit ×4, 8-bit ×278
	- Modules not listed below (attention projections, embeddings, `lm_head`, routers, norms, dense MLPs) are kept at 8-bit or full precision as the high-precision backbone.

	\| Module pattern \| Bits \| Count \|
	\|---\|---\|---\|
	\| `language_model.lm_head` \| 8-bit \| 1 \|
	\| `language_model.model.embed_tokens` \| 8-bit \| 1 \|
	\| `language_model.model.layers.{i}.mlp.down_proj` \| 8-bit \| 3 \|
	\| `language_model.model.layers.{i}.mlp.gate.gate` \| 8-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.gate_proj` \| 8-bit \| 3 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.down_proj` \| 4-bit \| 32 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.down_proj` \| 5-bit \| 8 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.down_proj` \| 6-bit \| 2 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.gate_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.share_expert.up_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.down_proj` \| 4-bit \| 32 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.down_proj` \| 5-bit \| 8 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.down_proj` \| 6-bit \| 2 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.gate_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.switch_mlp.up_proj` \| 4-bit \| 42 \|
	\| `language_model.model.layers.{i}.mlp.up_proj` \| 8-bit \| 3 \|
	\| `language_model.model.layers.{i}.self_attn.g_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.k_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.o_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.q_proj` \| 8-bit \| 45 \|
	\| `language_model.model.layers.{i}.self_attn.v_proj` \| 8-bit \| 45 \|