docs: Tier 1 polish — frontmatter + quickstart + KV-root rewrite

d11f624 verified 2 days ago

3.58 kB

license: other
license_name: nvidia-open-model-license
license_link: >-
  https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
base_model: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
tags:
  - nemotron
  - multimodal
  - mamba2
  - moe
  - quantized
  - turboquant
  - mlx
  - kv-cache-modifier
  - apple-silicon
  - runtime-modifier
  - matched-stack
library_name: mlx
pipeline_tag: text-generation
language:
  - en
datasets:
  - nvidia/Nemotron-Image-Training-v3
inference: false

Nemotron-3-Nano-Omni-30B-A3B-Reasoning - TurboQuant MLX 3-bit + TurboQuant KV-Cache (matched stack)

Documentation card for the matched TurboQuant weight + TurboQuant KV-cache stack of Nemotron-3-Nano-Omni-30B-A3B-Reasoning at MLX 3-bit.

No new weights are published here. Load the weights from majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-3bit and apply the TurboQuant KV-cache modifier documented in majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant.

Quickstart

This card pairs the TurboQuant weights with the TurboQuant KV-cache modifier (matched stack). Both are documentation-only — load the parent weight repo for actual MLX shards.

# Today (mlx-lm 0.31.x): the NemotronH_Nano_Omni_Reasoning_V3 model class
# is not yet registered in mlx-lm. The cell below is the API shape that WILL
# work once upstream lands the class (track ml-explore/mlx-lm#386).

from mlx_lm import load, generate

model, tokenizer = load("majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-3bit-TQ-KV")

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Solve: 17 * 23"}],
    add_generation_prompt=True,
    enable_thinking=False,  # set True to enable extended reasoning (default)
)

response = generate(
    model, tokenizer,
    prompt=prompt,
    max_tokens=512,
    sampler=lambda x: x.argmax(axis=-1),  # or use mlx_lm.sample_utils.make_sampler(temp=0.6, top_p=0.95)
)
print(response)

⚠️ This variant covers the text tower only. For multimodal inference (vision + audio + video), use the GGUF variants with llama-mtmd-cli — see the GGUF cards in this family.

Modality matrix

Modality	Encoder	Quantization in this variant
Text	LLM backbone (Mamba-2 + Transformer hybrid Sparse MoE)	per the variant suffix
Image	CRADIO v4-H	BF16 (kept full-precision in every non-GGUF variant; GGUF uses mmproj-F16 split file)
Audio	Parakeet-TDT-0.6B-v2	BF16 (same rationale)
Video	Parakeet-TDT-0.6B-v2 + frame sampler	BF16 (≤ 2 min, 256 frames @ 2 FPS)

NVIDIA's official FP8 / NVFP4 recipe keeps both encoders + the cross-modal MLP projectors in BF16 to preserve multimodal accuracy. We follow that convention in every quantized variant we ship.

Runtime quirks

MLX-LM (text-only)

This variant covers the LLM backbone only. Vision + audio encoders are NOT included — MLX-VLM Nemotron-Omni model class is pending upstream support (no PR observed as of 2026-05-04).

Use the mlx_lm.generate API; enable_thinking is a runtime flag (see below).

Reasoning mode

enable_thinking defaults to True. To disable extended reasoning (e.g., for latency-sensitive cases), pass enable_thinking=False to the chat template / generate call. No separate "no-think" variant card exists — this is a runtime flag, not a model variant.