Instructions to use RecursiveSI/flint-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RecursiveSI/flint-int4 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("RecursiveSI/flint-int4")

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)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use RecursiveSI/flint-int4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RecursiveSI/flint-int4"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RecursiveSI/flint-int4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use RecursiveSI/flint-int4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "RecursiveSI/flint-int4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "RecursiveSI/flint-int4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "RecursiveSI/flint-int4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use RecursiveSI/flint-int4 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 "RecursiveSI/flint-int4"

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 RecursiveSI/flint-int4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RecursiveSI/flint-int4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "RecursiveSI/flint-int4"

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 "RecursiveSI/flint-int4" \
  --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"

flint-int4 / config.json

alexey-recursive

Release Flint quantized checkpoint

2cb2bdc 1 day ago

Raw History Blame Contribute Delete

3.08 kB

{
  "architectures": [
    "FlintForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attention_sink": true,
  "bos_token_id": 150000,
  "decoder_sparse_step": 1,
  "dtype": "bfloat16",
  "eos_token_id": [
    150001,
    150003,
    150005,
    150018
  ],
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "intermediate_size": 6144,
  "kv_group_size": 64,
  "kv_key_bits": 8,
  "kv_value_bits": 8,
  "layer_types": [
    "full_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 262144,
  "mlp_only_layers": [
    0,
    1
  ],
  "mlx_export": {
    "bits": 4,
    "embedding_bits": 8,
    "full_attention_layers": [
      0,
      1,
      5,
      9,
      13,
      17,
      21,
      25,
      29,
      33,
      37,
      41,
      45,
      48
    ],
    "routed_expert_bits": 4,
    "scale_rule": "mse"
  },
  "model_type": "flint",
  "moe_intermediate_size": 512,
  "no_rope_layer_indices": [
    0,
    1,
    5,
    9,
    13,
    17,
    21,
    25,
    29,
    33,
    37,
    41,
    45,
    48
  ],
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts": 256,
  "num_experts_per_tok": 6,
  "num_hidden_layers": 49,
  "num_key_value_heads": 4,
  "num_local_experts": 256,
  "output_router_logits": false,
  "quantization": {
    "bits": 4,
    "group_size": 64
  },
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "rope_theta": 10000.0,
  "router_aux_loss_coef": 0.0,
  "router_expert_bias": false,
  "scoring_func": "sigmoid",
  "shared_expert_intermediate_size": 1024,
  "sliding_window": 513,
  "softmax_type": "learnable",
  "softmax_type_source": "model.attention_pattern.softmax_type",
  "tie_word_embeddings": false,
  "use_cache": true,
  "use_sliding_window": true,
  "vocab_size": 150144,
  "router_score_function": "sigmoid",
  "torch_dtype": "bfloat16",
  "pad_token_id": 150001
}

	{
	"architectures": [
	"FlintForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_sink": true,
	"bos_token_id": 150000,
	"decoder_sparse_step": 1,
	"dtype": "bfloat16",
	"eos_token_id": [
	150001,
	150003,
	150005,
	150018
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"intermediate_size": 6144,
	"kv_group_size": 64,
	"kv_key_bits": 8,
	"kv_value_bits": 8,
	"layer_types": [
	"full_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 262144,
	"mlp_only_layers": [
	0,
	1
	],
	"mlx_export": {
	"bits": 4,
	"embedding_bits": 8,
	"full_attention_layers": [
	0,
	1,
	5,
	9,
	13,
	17,
	21,
	25,
	29,
	33,
	37,
	41,
	45,
	48
	],
	"routed_expert_bits": 4,
	"scale_rule": "mse"
	},
	"model_type": "flint",
	"moe_intermediate_size": 512,
	"no_rope_layer_indices": [
	0,
	1,
	5,
	9,
	13,
	17,
	21,
	25,
	29,
	33,
	37,
	41,
	45,
	48
	],
	"norm_topk_prob": true,
	"num_attention_heads": 32,
	"num_experts": 256,
	"num_experts_per_tok": 6,
	"num_hidden_layers": 49,
	"num_key_value_heads": 4,
	"num_local_experts": 256,
	"output_router_logits": false,
	"quantization": {
	"bits": 4,
	"group_size": 64
	},
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	},
	"rope_theta": 10000.0,
	"router_aux_loss_coef": 0.0,
	"router_expert_bias": false,
	"scoring_func": "sigmoid",
	"shared_expert_intermediate_size": 1024,
	"sliding_window": 513,
	"softmax_type": "learnable",
	"softmax_type_source": "model.attention_pattern.softmax_type",
	"tie_word_embeddings": false,
	"use_cache": true,
	"use_sliding_window": true,
	"vocab_size": 150144,
	"router_score_function": "sigmoid",
	"torch_dtype": "bfloat16",
	"pad_token_id": 150001
	}