Instructions to use inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 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("inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4")

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 inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4"

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": "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 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 "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4"

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 inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4"

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 "inferencerlabs/NVIDIA-Nemotron-3-Super-120B-A12B-MLX-Q4" \
  --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"

inferencerlabs commited on Mar 12

Commit

4f4d524

verified ·

1 Parent(s): eb87fd2

Upload model file

Browse files

Files changed (1) hide show

config.json +83 -0

config.json ADDED Viewed

	@@ -0,0 +1,83 @@

+{
+    "architectures": [
+        "NemotronHForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_nemotron_h.NemotronHConfig",
+        "AutoModelForCausalLM": "modeling_nemotron_h.NemotronHForCausalLM"
+    },
+    "bos_token_id": 1,
+    "chunk_size": 128,
+    "conv_kernel": 4,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        2,
+        11
+    ],
+    "expand": 2,
+    "head_dim": 128,
+    "hidden_dropout": 0.0,
+    "hidden_size": 4096,
+    "hybrid_override_pattern": "MEMEMEM*EMEMEMEM*EMEMEMEM*EMEMEMEMEM*EMEMEMEMEM*EMEMEMEMEM*EMEMEMEMEM*EMEMEMEM*EMEMEMEME",
+    "initializer_range": 0.02,
+    "intermediate_size": 2688,
+    "layer_norm_epsilon": 1e-05,
+    "mamba_head_dim": 64,
+    "mamba_hidden_act": "silu",
+    "mamba_num_heads": 128,
+    "mamba_proj_bias": false,
+    "mamba_ssm_cache_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_bias": false,
+    "mlp_hidden_act": "relu2",
+    "mlx-sanitized": "0.30.7",
+    "model_type": "nemotron_h",
+    "moe_intermediate_size": 2688,
+    "moe_latent_size": 1024,
+    "moe_shared_expert_intermediate_size": 5376,
+    "moe_shared_expert_overlap": false,
+    "mtp_hybrid_override_pattern": "*E",
+    "n_group": 1,
+    "n_groups": 8,
+    "n_routed_experts": 512,
+    "n_shared_experts": 1,
+    "norm_eps": 1e-05,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts_per_tok": 22,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 2,
+    "num_logits_to_keep": 1,
+    "num_nextn_predict_layers": 1,
+    "pad_token_id": 0,
+    "partial_rotary_factor": 1.0,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rescale_prenorm_residual": true,
+    "residual_in_fp32": false,
+    "rope_theta": 10000,
+    "routed_scaling_factor": 5.0,
+    "sliding_window": null,
+    "ssm_state_size": 128,
+    "tie_word_embeddings": false,
+    "time_step_floor": 0.0001,
+    "time_step_max": 0.1,
+    "time_step_min": 0.001,
+    "topk_group": 1,
+    "transformers_version": "4.57.6",
+    "use_bias": false,
+    "use_cache": true,
+    "use_conv_bias": true,
+    "use_mamba_kernels": true,
+    "vocab_size": 131072
+}