Downloads · 30 days
61.7K
18% of all-time downloads
zenmagnets/Nemotron-3-Embed-1B-Q4_K_M-GGUF
Nemotron-3-Embed-1B-Q4_K_M-GGUF is a sentence similarity model from zenmagnets. Use it when you need a score for how close two texts are. It is set up for gguf. The card lists the license as openmdw-1.1.
An independently converted and quantized GGUF of NVIDIA's nvidia/Nemotron-3-Embed-1B-BF16, prepared for local embedding inference in LM Studio and llama.cpp-compatible runtimes.
Downloads · 30 days
61.7K
18% of all-time downloads
All-time downloads
334K
Public
Repo size
749 MB
Likes
7
Public
Click a slice to open those files.
.gguf749 MB · 100%
From the Hugging Face model README
An independently converted and quantized GGUF of NVIDIA's
nvidia/Nemotron-3-Embed-1B-BF16,
prepared for local embedding inference in LM Studio and llama.cpp-compatible runtimes.
This repository is not an official NVIDIA release and is not affiliated with or endorsed by NVIDIA.
| File | Quantization | Size | SHA-256 |
|---|---|---|---|
nemotron-3-embed-1b-q4_k_m.gguf | Q4_K_M | 749,352,096 bytes (714.6 MiB) | 9a74166f51dbc280073748fa199bea49283bd21f7f9280f2dec2b4d975ddfd1d |
The model produces 2,048-dimensional, L2-normalized embeddings. Its GGUF metadata declares a 262,144-token maximum context. The release was functionally tested at a 4,096-token context; very large contexts were not validated and require substantially more memory.
Download the GGUF from Files and versions, then drag it into LM Studio or place it in LM Studio's models directory. LM Studio should classify it as an embedding model.
Load it with a 4,096-token context and full GPU offload, start the local server, and call the OpenAI-compatible embeddings endpoint:
curl http://127.0.0.1:1234/v1/embeddings \
-H 'Content-Type: application/json' \
-d '{
"model": "nemotron-3-embed-1b-q4",
"input": [
"query: What is retrieval-augmented generation?",
"passage: Retrieval-augmented generation adds retrieved documents to a model prompt."
]
}'
The exact model identifier can differ if LM Studio assigns another load name; check
http://127.0.0.1:1234/v1/models when needed.
Use the prefixes specified by NVIDIA:
query: <text>passage: <text>Embeddings are normalized, so cosine similarity and dot product give equivalent rankings (within normal floating-point tolerance).
nvidia/Nemotron-3-Embed-1B-BF160677b2025cbc37daf92d7b9c7a225de8cfbc5b0bllama.cpp build b10015, commit 12127defda4f41b7679cb2477a4b0d65ee6a0c8fThe conversion was mechanical. The model was not fine-tuned or otherwise trained. See
QUANTIZATION.md for the reproducibility record and embedded metadata summary.
Validated on an Apple M3 Max with LM Studio 0.4.19 Build 2 and its llama.cpp runtime 2.25.2, using full GPU offload and a 4,096-token context.
| Check | Result |
|---|---|
| Output dimensions | 2,048 |
| L2 norm (three test vectors) | 1.00000002 / 1.00000001 / 0.99999997 |
| Relevant query/passage cosine | 0.654999 |
| Unrelated query/passage cosine | 0.044103 |
| Median latency, one input | 30.46 ms |
| Median batch time, 32 inputs | 974.98 ms |
| Median batch throughput | 32.82 texts/s |
Latency includes local HTTP and JSON serialization. These numbers are a runtime smoke test, not a retrieval-quality evaluation. Hardware, text length, context settings, and runtime versions affect performance.
The model materials are distributed under the OpenMDW License Agreement 1.1. The upstream model incorporates Ministral-3-3B-Instruct-2512 materials released under Apache 2.0.
This repository retains NVIDIA's LICENSE, NOTICE, and
THIRD_PARTY_NOTICES.md. By using or distributing the model, you agree to
the applicable license terms. NVIDIA retains ownership of its names and trademarks; their use here
is solely to identify the upstream model.