Instructions to use OsaurusAI/LFM2.5-2.6B-MXFP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/LFM2.5-2.6B-MXFP8 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("OsaurusAI/LFM2.5-2.6B-MXFP8")

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 OsaurusAI/LFM2.5-2.6B-MXFP8 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/LFM2.5-2.6B-MXFP8"

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": "OsaurusAI/LFM2.5-2.6B-MXFP8"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use OsaurusAI/LFM2.5-2.6B-MXFP8 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 "OsaurusAI/LFM2.5-2.6B-MXFP8"

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 OsaurusAI/LFM2.5-2.6B-MXFP8

Run Hermes

hermes

OpenClaw new

How to use OsaurusAI/LFM2.5-2.6B-MXFP8 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/LFM2.5-2.6B-MXFP8"

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 "OsaurusAI/LFM2.5-2.6B-MXFP8" \
  --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 OsaurusAI/LFM2.5-2.6B-MXFP8 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/LFM2.5-2.6B-MXFP8"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/LFM2.5-2.6B-MXFP8"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/LFM2.5-2.6B-MXFP8",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

LFM2.5-2.6B-MXFP8 / config.json

Osaurus-AI

LFM2.5-2.6B MXFP8: e4m3/e8m0 gs32 + AWQ folds + GPTQ codes-only QAT

490b8d4 verified about 9 hours ago

Raw

History Blame Contribute Delete

2.94 kB

	{
	"architectures": [
	"Lfm2ForCausalLM"
	],
	"block_auto_adjust_ff_dim": false,
	"block_dim": 2048,
	"block_ffn_dim_multiplier": 1.0,
	"block_mlp_init_scale": 1.0,
	"block_multiple_of": 256,
	"block_norm_eps": 1e-05,
	"block_out_init_scale": 1.0,
	"block_use_swiglu": true,
	"block_use_xavier_init": true,
	"bos_token_id": 124894,
	"conv_L_cache": 3,
	"conv_bias": false,
	"conv_dim": 2048,
	"conv_use_xavier_init": true,
	"dtype": "bfloat16",
	"eos_token_id": [
	124900
	],
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 10752,
	"layer_types": [
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv",
	"full_attention",
	"conv",
	"conv"
	],
	"max_position_embeddings": 128000,
	"model_type": "lfm2",
	"norm_eps": 1e-05,
	"num_attention_heads": 32,
	"num_heads": 32,
	"num_hidden_layers": 30,
	"num_key_value_heads": 8,
	"pad_token_id": 124893,
	"rope_parameters": {
	"rope_theta": 10000000.0,
	"rope_type": "default"
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.2.0",
	"use_cache": true,
	"use_pos_enc": true,
	"vocab_size": 128000,
	"block_ff_dim": 10752,
	"rope_theta": 10000000.0,
	"weight_format": "mxfp8",
	"quantization": {
	"group_size": 32,
	"bits": 8,
	"mode": "mxfp8"
	},
	"quantization_config": {
	"group_size": 32,
	"bits": 8,
	"mode": "mxfp8"
	},
	"jang_runtime": {
	"architecture": "lfm2_hybrid",
	"cache_layout": "lfm2_hybrid_v1",
	"num_hidden_layers": 30,
	"full_attention_layers": [
	2,
	5,
	9,
	13,
	17,
	21,
	24,
	27
	],
	"num_conv_layers": 22,
	"conv_L_cache": 3,
	"conv_kernel_layout": "hf_channels_first",
	"cache": {
	"full_attention": "kv",
	"conv": "arrays_state_size_1"
	},
	"norm_convention": "llama_rmsnorm_no_plus_one",
	"qk_norm": "per_head_rmsnorm",
	"rope": {
	"type": "neox",
	"theta": 10000000.0,
	"dims": 64,
	"applied_after_qk_norm": true
	},
	"attention": {
	"type": "gqa",
	"n_heads": 32,
	"n_kv_heads": 8,
	"head_dim": 64
	},
	"tied_embeddings": true
	},
	"capabilities": {
	"reasoning_parser": "qwen3",
	"tool_parser": "lfm2",
	"think_in_template": true,
	"supports_tools": true,
	"supports_thinking": true,
	"family": "lfm2",
	"modality": "text",
	"modalities": {
	"text": true,
	"vision": false,
	"audio": false,
	"video": false
	},
	"has_vision": false,
	"has_audio": false,
	"has_video": false,
	"cache_type": "hybrid"
	}
	}