Instructions to use majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit 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("majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit")

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 majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit"

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": "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit 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 "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit"

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 majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit

Run Hermes

hermes

OpenClaw new

How to use majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit"

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 "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit" \
  --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 majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Nemotron-3-Nano-4B-TurboQuant-MLX-2bit / README.md

majentik

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip

e3e8b9e verified 11 days ago

preview code

Raw

History Blame Contribute Delete

5.71 kB

	---
	base_model: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
	library_name: mlx
	tags:
	- turboquant
	- kv-cache-quantization
	- nemotron
	- nvidia
	- mamba2
	- hybrid
	- quantized
	- mlx
	- 2bit
	license: other
	license_name: nvidia-open-model-license
	license_link: https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
	pipeline_tag: text-generation
	---

	> [!TIP]
	> KV-cache quantization without any fork (recommended, 2026): upstream
	> llama.cpp/Ollama now cover this natively — use `-ctk q8_0 -ctv q8_0`
	> (~half KV memory, negligible quality loss: perplexity +0.002–0.05) or
	> `-ctk q4_0 -ctv q4_0` (~quarter memory, ≈7.6% perplexity increase). In
	> Ollama: `OLLAMA_KV_CACHE_TYPE=q8_0` with `OLLAMA_FLASH_ATTENTION=1`. Keep
	> K and V types symmetric to stay on the fast fused Flash-Attention path.
	> Since April 2026, mainline llama.cpp also applies Hadamard rotation to
	> KV activations ([PR #21038](https://github.com/ggml-org/llama.cpp/pull/21038)),
	> which greatly improves low-bit KV quality (opt-out:
	> `LLAMA_ATTN_ROT_DISABLE=1`).
	>
	> The RotorQuant/TurboQuant fork flow below is experimental/legacy: the
	> TurboQuant llama.cpp PR was closed without merging (June 2026) and the fork
	> is unmaintained relative to mainline. It is NOT required to use this model.
	<!-- kv-upstream-note -->

	# Nemotron-3-Nano-4B - TurboQuant MLX 2-bit

	2-bit weight-quantized MLX version of [nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16) with the legacy TurboQuant KV-cache fork (superseded by upstream llama.cpp KV options). Optimized for Apple Silicon inference via the [MLX](https://github.com/ml-explore/mlx) framework. Maximum compression for running on memory-constrained devices. The dense hybrid Mamba-2 + Attention architecture supports up to 262K context length.

	Approximate model size: ~1.2 GB

	## Model Specifications

	\| Property \| Value \|
	\|---\|---\|
	\| Base Model \| [nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16) \|
	\| Parameters \| 4 billion (dense) \|
	\| Architecture \| Hybrid Mamba-2 + Attention (dense) \|
	\| Context Length \| 262,144 tokens (262K) \|
	\| License \| NVIDIA Open Model License (commercial use OK) \|
	\| Weight Quantization \| 2-bit (~1.2 GB) \|
	\| KV-Cache Quantization \| TurboQuant \|
	\| Framework \| MLX (Apple Silicon) \|

	## Quickstart

	```python
	from mlx_lm import load, generate
	from turboquant import TurboQuantCache

	model, tokenizer = load("majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-2bit")

	prompt = "Explain the theory of relativity."
	response = generate(model, tokenizer, prompt=prompt, max_tokens=512)
	print(response)
	```

	## About the RotorQuant / TurboQuant labels

	RotorQuant and TurboQuant are this project's release labels, not distinct
	quantization algorithms — for any given tier, both brand repos carry
	byte-identical weights produced with the standard MLX / llama.cpp quantizers.
	No brand-specific speedup is claimed or measured. The KV-cache fork these
	labels originally referred to is legacy; for KV-cache memory savings use the
	upstream options described above (`-ctk/-ctv q8_0`, `OLLAMA_KV_CACHE_TYPE`).

	## KV-Cache Quantization Comparison

	\| Method \| Prefill Speed \| Decode Speed \| Memory Savings \| Reference \|
	\|---\|---\|---\|---\|---\|
	\| TurboQuant \| 1x (baseline) \| 1x (baseline) \| High \| [arXiv: 2504.19874](https://arxiv.org/abs/2504.19874) \|


	## Memory Estimates (Nemotron-3-Nano-4B)

	\| Precision \| Approximate Size \| MLX Variant \|
	\|---\|---\|---\|
	\| BF16 (original) \| ~8 GB \| -- \|
	\| 8-bit quantized \| ~4 GB \| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-8bit) \|
	\| 4-bit quantized \| ~2.3 GB \| [TurboQuant-MLX-4bit](https://huggingface.co/majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-4bit) \|
	\| 2-bit quantized \| ~1.2 GB \| This model \|

	## Hardware Requirements

	This model requires approximately 1.2 GB of unified memory. Recommended hardware:
	- Apple M1 (8 GB+)
	- Apple M2 (8 GB+)
	- Apple M3 (8 GB+)
	- Apple M4 (8 GB+)
	- Any Apple Silicon Mac with 8 GB+ unified memory

	## See Also

	- [nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16) -- Base model
	- [majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-8bit](https://huggingface.co/majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-8bit) -- MLX 8-bit variant
	- [majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-4bit](https://huggingface.co/majentik/Nemotron-3-Nano-4B-TurboQuant-MLX-4bit) -- MLX 4-bit variant
	- [majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-2bit](https://huggingface.co/majentik/Nemotron-3-Nano-4B-RotorQuant-MLX-2bit) -- RotorQuant MLX 2-bit variant
	- [TurboQuant Paper (arXiv: 2504.19874)](https://arxiv.org/abs/2504.19874)
	- [MLX Framework](https://github.com/ml-explore/mlx)

	## Quant trade-off (MLX lane)

	\| Bits \| Approx size \| Use case \| Recommendation \|
	\|---\|---\|---\|---\|
	\| 2-bit \| ~1.0 GB \| Aggressive quantization \| Very low-RAM Macs \|
	\| 3-bit \| ~1.4 GB \| Lossy but small \| Low-RAM Macs \|
	\| 4-bit \| ~1.7 GB \| Balanced default \| Recommended for most Macs \|
	\| 5-bit \| ~2.0 GB \| Higher fidelity \| Quality-sensitive \|
	\| 6-bit \| ~2.4 GB \| Approaching FP16 quality \| High-fidelity \|
	\| 8-bit \| ~3.0 GB \| Near-lossless reference \| Fidelity-critical work \|

	(Current variant — 2bit — is bolded.)

	## Variants in this family

	(Showing 13 sibling variants under `majentik/nemotron3-nano-4b-`. The current variant — `TurboQuant-MLX-2bit` — is bolded*.)

	\| Variant \| Runtime \| Approx size \| Use case \|
	\|---\|---\|---\|---\|
	\| TurboQuant-MLX-2bit \| mlx-lm \| ~1.3 GB \| Apple Silicon, smallest \|