---
title: Nemotron-3-Embed-1B-BF16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Nemotron-3-Embed-1B-BF16"
md_url: "https://www.modelscope.cn/models/mlx-community/Nemotron-3-Embed-1B-BF16.md"
repository: mlx-community/Nemotron-3-Embed-1B-BF16
last_updated: 2026-08-04
license: openmdw-1.1
pipeline_tag: sentence-similarity
tasks:
  - sentence-similarity
model_type:
  - ministral3
architectures:
  - Ministral3Model
base_model:
  - nvidia/Nemotron-3-Embed-1B-BF16
base_model_relation: finetune
parameters: 1.1B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ar
  - as
  - bn
  - bg
  - zh
  - da
  - nl
  - fi
  - fr
  - de
  - hi
  - id
  - it
  - ja
  - ko
  - ms
  - mr
  - ne
  - no
  - fa
  - pt
  - ro
  - ru
  - es
  - sw
  - sv
  - ta
  - te
  - th
  - uk
  - ur
  - vi
  - multilingual
downloads: 63
stars: 0
tags:
  - mlx
  - sentence-similarity
  - feature-extraction
  - retrieval
  - embeddings
---

# Nemotron-3-Embed-1B-BF16

> Nemotron-3-Embed-1B-BF16 - mlx-community 在 ModelScope 开源的模型。Nemotron-3-Embed-1B-BF16

mlx-community/Nemotron-3-Embed-1B-BF16 是 ModelScope 魔搭社区上的 1.1B 参数sentence-similarity模型，采用 openmdw-1.1 许可，基于 nvidia/Nemotron-3-Embed-1B-BF16 构建。

- **Repository**: mlx-community/Nemotron-3-Embed-1B-BF16
- **License**: openmdw-1.1
- **Tasks**: sentence-similarity
- **Parameters**: 1.1B
- **Base model**: nvidia/Nemotron-3-Embed-1B-BF16
- **Tags**: mlx, sentence-similarity, feature-extraction, retrieval, embeddings
- **Downloads**: 63
- **Stars**: 0
- **Last updated**: 2026-08-04

Source: https://www.modelscope.cn/models/mlx-community/Nemotron-3-Embed-1B-BF16

---

# Nemotron-3-Embed-1B-BF16

An **MLX conversion** of [`nvidia/Nemotron-3-Embed-1B-BF16`](https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16) that runs
natively on Apple Silicon. Weights are kept at the original bfloat16 precision.

This is an **independent community conversion**. It is **not affiliated with or
endorsed by NVIDIA**. The original model ships vLLM (CUDA) and PyTorch paths
only; this repository fills the MLX gap and bundles a self-contained
implementation.

The repository name keeps the upstream `-BF16` suffix on purpose: NVIDIA
publishes both a BF16 and an NVFP4 checkpoint, and this conversion is derived
from the **BF16** one.

Mirrored from [`choipilkyu/Nemotron-3-Embed-1B-BF16-MLX`](https://huggingface.co/choipilkyu/Nemotron-3-Embed-1B-BF16-MLX),
where these weights were first published.

## Changes from the original

The original architecture `Ministral3Model` is a bidirectional-attention encoder,
which `mlx-lm` / `mlx-embeddings` do not support out of the box. The following
changes were made, and the implementation is bundled as a single self-contained
file, [`nemotron3_embed_mlx.py`](nemotron3_embed_mlx.py):

1. Reused attention, yarn RoPE and llama_4_scaling from the `ministral3` causal-LM
   implementation in `mlx-lm`.
2. Removed the causal mask and replaced it with a key-padding mask, turning the
   stack into a **bidirectional encoder**.
3. Applied mean pooling + L2 normalization. Pooling and normalization run in fp32
   to avoid bf16 accumulation error perturbing the embedding norm.
4. No quantization applied (bfloat16 retained).

No weights were retrained. Numerics are unchanged apart from the quantization
noted above.

## Verification

Checked against the original PyTorch implementation (fp32, identical token ids):
worst-case cosine similarity of the pooled embedding **> 0.999**.

| Check | This build |
|---|---|
| Source revision converted | [`a5e0f804b9e9`](https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16/tree/a5e0f804b9e90a1ca6784ecbf6e41595774fc834) |
| `model.safetensors` sha256 | `99e5798884d3aa650db76f5fdecbc44ac25480bf14aaf9d9fde0065701abb2bb` |
| Embedding L2 norm (min–max) | 1.000000 – 1.000000 |

Embeddings are L2-normalized exactly, not approximately: pooling and
normalization run in fp32 so bf16 accumulation cannot drift the norm.

## Quantization impact

This repository is a **format conversion**, not a new model. Absolute retrieval
quality belongs to the upstream model — see
[`nvidia/Nemotron-3-Embed-1B-BF16`](https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16) and NVIDIA's published benchmark
figures. This card therefore does not restate absolute quality; it measures the
two things the conversion itself can change: **fidelity to the original**
(above) and **what quantization costs**.

Measured on an Apple M4 (32GB). Every variant saw identical task data on the same
machine, which is what makes the comparison valid:

| Variant | Size | NDCG@10 retention | Recall@10 retention |
|---|---|---|---|
| [`Nemotron-3-Embed-1B-BF16`](https://huggingface.co/mlx-community/Nemotron-3-Embed-1B-BF16) | 2.28 GB | 100.0% | 100.0% |
| [`Nemotron-3-Embed-1B-BF16-8bit`](https://huggingface.co/mlx-community/Nemotron-3-Embed-1B-BF16-8bit) | 1.21 GB | 100.0% | 100.0% |
| [`Nemotron-3-Embed-1B-BF16-4bit`](https://huggingface.co/mlx-community/Nemotron-3-Embed-1B-BF16-4bit) | 0.64 GB | 99.3% | 98.7% |

Retention is the per-dataset ratio to bf16, averaged over the nine tasks below.

**NanoBEIR** — 4 of the 13 tasks, each on its full corpus, so these per-task
figures are directly comparable to other published NanoBEIR per-task numbers.
The 4-task average is not comparable to a published 13-task mean, so none is
given.

NDCG@10 per dataset:

| Dataset | bf16 | 8bit | 4bit |
|---|---|---|---|
| NanoNQ · en | 0.7482 | 0.7418 | 0.7565 |
| NanoFiQA2018 · en | 0.6355 | 0.6387 | 0.6017 |
| NanoSciFact · en | 0.7821 | 0.7818 | 0.7894 |
| NanoNFCorpus · en | 0.3653 | 0.3666 | 0.3608 |

Recall@10 per dataset:

| Dataset | bf16 | 8bit | 4bit |
|---|---|---|---|
| NanoNQ · en | 0.8800 | 0.8800 | 0.8900 |
| NanoFiQA2018 · en | 0.7407 | 0.7407 | 0.7069 |
| NanoSciFact · en | 0.8700 | 0.8700 | 0.8700 |
| NanoNFCorpus · en | 0.1492 | 0.1498 | 0.1384 |

**MIRACL** — dev-split hard-negatives corpus **subsampled to ~6k passages per
language** (every judged document kept; distractors drawn with a fixed seed, so
all variants face the identical task). Subsampling inflates the absolute
numbers, so **these are for relative comparison between variants only** and must
not be read against published full-corpus MIRACL results. A second reason not to
read them as quality figures: NVIDIA lists `MIRACLRetrieval` among the upstream
model's [training datasets](https://huggingface.co/nvidia/Nemotron-3-Embed-1B-BF16), so MIRACL is
in-domain for this model, not a zero-shot benchmark. Neither caveat affects the
retention comparison, which is what these rows are here for.

NDCG@10 per dataset:

| Dataset | bf16 | 8bit | 4bit |
|---|---|---|---|
| MIRACL · ar | 0.8920 | 0.8918 | 0.8895 |
| MIRACL · de | 0.8067 | 0.8074 | 0.8009 |
| MIRACL · es | 0.8582 | 0.8593 | 0.8584 |
| MIRACL · ja | 0.8658 | 0.8663 | 0.8637 |
| MIRACL · ko | 0.8143 | 0.8157 | 0.8086 |

Recall@10 per dataset:

| Dataset | bf16 | 8bit | 4bit |
|---|---|---|---|
| MIRACL · ar | 0.9873 | 0.9870 | 0.9884 |
| MIRACL · de | 0.9614 | 0.9614 | 0.9597 |
| MIRACL · es | 0.9788 | 0.9788 | 0.9790 |
| MIRACL · ja | 0.9851 | 0.9851 | 0.9839 |
| MIRACL · ko | 0.9185 | 0.9185 | 0.9146 |

Reproduce with the bundled [`benchmark_mteb.py`](benchmark_mteb.py):
`pip install mteb datasets` then `python benchmark_mteb.py . results.json`.

## Usage

```bash
pip install mlx mlx-lm transformers numpy huggingface_hub
```

```python
import sys
from huggingface_hub import snapshot_download

path = snapshot_download("mlx-community/Nemotron-3-Embed-1B-BF16")
sys.path.insert(0, path)
from nemotron3_embed_mlx import load, encode

model, tokenizer = load(path)
q = encode(model, tokenizer, ["What is the refund policy?"], input_type="query")
d = encode(model, tokenizer,
           ["Full refunds are available within 14 days of purchase."],
           input_type="passage")
print(float(q[0] @ d[0]))   # embeddings are L2-normalized, so dot == cosine
```

**Prefixes matter.** Queries need `query: ` and documents need `passage: `.
The `input_type` argument applies them for you; pass `input_type=None` if you
have already added the prefix yourself.

## Repository contents

The sentence-transformers scaffolding files (`modules.json`, `1_Pooling/`,
`sentence_bert_config.json`, `config_sentence_transformers.json`) are carried
over from the upstream repository as configuration reference. **These weights
load only via the bundled MLX implementation** — not via `sentence-transformers`
or `transformers`.

## Choosing a variant

Measured on an M1 Pro (16GB) over 200 documents averaging 1,014 characters,
batch size 8:

| Backend | Throughput | Weights |
|---|---|---|
| upstream via PyTorch/MPS (sentence-transformers) | 1.53 docs/s | 2.28 GB |
| this port, bf16 | **2.71 docs/s** | 2.28 GB |
| this port, 8-bit | 1.66 docs/s | 1.21 GB |
| this port, 4-bit | 1.65 docs/s | 0.64 GB |

Two things follow. At identical precision the MLX path is **1.8x faster** than
the upstream PyTorch/MPS path. But the quantized variants are **~1.6x slower
than bf16, not faster**: at 1.1B parameters the dequantization cost outweighs
the reduced memory traffic. The same ordering shows up in the Apple M4 runs
above (bf16 2.5 docs/s, 8-bit and 4-bit 2.2 docs/s).

**Pick bf16 for throughput. Pick 8-bit or 4-bit for footprint** — 0.64 GB fits
alongside other work on a small machine, and keeps 99.3% NDCG retention.

Reproduce on your own machine with the bundled
[`compare_backends.py`](compare_backends.py).

## Limitations

- Default `max_length` is 4096. The original supports 32k, but bidirectional
  attention is O(L²) and memory becomes the binding constraint well before that.
- Throughput on Apple Silicon is modest: 2.5 docs/s on long Korean
  documents (avg 1,014 chars, batch 8) measured on an Apple M4 (32GB). Use a server for
  bulk indexing and this for development and interactive querying, where
  single-query latency is not a problem.
- Embeddings from different variants are not interchangeable. Do not mix
  outputs of different variants in one index.

## License

The original model is licensed by NVIDIA under **OpenMDW-1.1**, and its base
model `mistralai/Ministral-3-3B-Instruct-2512` under Apache-2.0. Both texts are
bundled here as [`LICENSE`](LICENSE) and [`NOTICE`](NOTICE).

Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.