NE

Nemotron 3.5 Embed 1B BF16

NemotronGGUF by W4DUpdated 2026-10-22
Download on Hugging Face
Parameters1.14B
Context256K
Layers16
Architecturemistral3
Smallest quant0.0 GB
Quick answer

Nemotron 3.5 Embed 1B BF16 needs about 1.8 GB of memory at Q4_K_M (a 0.7 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 35 quants, from 0.0 GB to 4.6 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.

1.14B‑parameter multimodal embedding model

Nemotron 3.5 Embed 1B BF16 is a multimodal embedding model that supports text and document‑image inputs. It produces 2048‑dimensional L2‑normalized embeddings. The model is trained on 262,144‑token context and is suitable for dense retrieval tasks.

Good at

  • Multilingual document retrieval
  • Image‑text embedding
  • Dense retrieval with 2048‑dim vectors

Limits

  • No vision support in current llama.cpp embedding endpoint
  • Requires 32,768‑token context for full capability
  • License governed by OpenMDW 1.1

Best for

  • Building multimodal search engines
  • Vectorizing large document corpora
  • Retrieval‑augmented applications

Who it’s for. Developers and researchers building multimodal question‑answer systems or dense retrieval pipelines. The model can be used for commercial or non‑commercial projects under the OpenMDW 1.1 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.0 GB
Fits Get file →
Q1_00.4 GB 1.4 GB
Fits Get file →
IQ1_S0.4 GB 1.4 GB
Fits Get file →
IQ1_M0.4 GB 1.4 GB
Fits Get file →
TQ1_00.4 GB 1.4 GB
Fits Get file →
IQ2_XXS0.4 GB 1.5 GB
Fits Get file →
IQ2_XS0.4 GB 1.5 GB
Fits Get file →
TQ2_00.5 GB 1.5 GB
Fits Get file →
IQ2_S0.5 GB 1.5 GB
Fits Get file →
Q2_00.5 GB 1.5 GB
Fits Get file →
IQ2_M0.5 GB 1.5 GB
Fits Get file →
Q2_K_S0.5 GB 1.6 GB
Fits Get file →
IQ3_XXS0.5 GB 1.6 GB
Fits Get file →
Q2_K0.5 GB 1.6 GB
Fits Get file →
IQ3_XS0.6 GB 1.6 GB
Fits Get file →
IQ3_S0.6 GB 1.6 GB
Fits Get file →
Q3_K_S0.6 GB 1.6 GB
Fits Get file →
IQ3_M0.6 GB 1.7 GB
Fits Get file →
Q3_K_M0.6 GB 1.7 GB
Fits Get file →
Q3_K_L0.7 GB 1.7 GB
Fits Get file →
IQ4_XS0.7 GB 1.7 GB
Fits Get file →
Q4_00.7 GB 1.8 GB
Fits Get file →
IQ4_NL0.7 GB 1.8 GB
Fits Get file →
Q4_K_S0.7 GB 1.8 GB
Fits Get file →
Q4_K_M0.7 GB 1.8 GB
Fits Get file →
Q4_10.8 GB 1.8 GB
Fits Get file →
Q5_00.8 GB 1.9 GB
Fits Get file →
Q5_K_S0.8 GB 1.9 GB
Fits Get file →
Q5_K_M0.8 GB 1.9 GB
Fits Get file →
Q5_10.9 GB 1.9 GB
Fits Get file →
Q6_K0.9 GB 2.0 GB
Fits Get file →
Q8_01.2 GB 2.3 GB
Fits Get file →
BF162.3 GB 3.3 GB
Fits Get file →
F162.3 GB 3.3 GB
Fits Get file →
F324.6 GB 5.6 GB
Fits Get file →

For 8 GB VRAM use Q8_0 (file size 1.22 GB, estimated 2.3 GB at 8 k context). With 6 GB VRAM Q6_K (0.94 GB, 2 GB). For 4 GB VRAM use Q5_K_M (0.84 GB, 1.9 GB). Higher quant levels increase accuracy but require more memory.

What GPU do you need for Nemotron 3.5 Embed 1B BF16?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is BF16 (2.3 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is F32 (4.6 GB file, about 5.6 GB in use).

Which Nemotron 3.5 Embed 1B BF16 quant should you choose?

Q4_K_M is the usual starting point for Nemotron 3.5 Embed 1B BF16: it balances file size and quality well. Here it is a 0.7 GB file.

The Q8_0 file is 1.2 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturemistral3
Parameters1.14B
Layers16
Trained context262,144 tokens
KV cache (fp16)64 KB per token

Source

Quantized byW4D
FamilyNemotron
Licenseother
Downloads (HF)2,963
Last updated2026-10-22

Frequently asked questions about Nemotron 3.5 Embed 1B BF16

How much VRAM does Nemotron 3.5 Embed 1B BF16 need?

About 1.8 GB at Q4_K_M with an 8K context window. That is the 0.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Nemotron 3.5 Embed 1B BF16 on an 8 GB GPU?

Yes, with F32: the 4.6 GB file needs about 5.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Nemotron 3.5 Embed 1B BF16 GGUF?

It depends on the quant: file is 0.0 GB, Q1_0 is 0.4 GB, IQ1_S is 0.4 GB, IQ1_M is 0.4 GB, TQ1_0 is 0.4 GB, IQ2_XXS is 0.4 GB and 29 more.

What context length does Nemotron 3.5 Embed 1B BF16 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.

Where can I download Nemotron 3.5 Embed 1B BF16 GGUF?

The files are on Hugging Face in the W4D/Nemotron-3.5-Embed-1B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Nemotron 3.5 Embed 1B BF16 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the Q8_0 quantization requires approximately 2.3 GB at 8 k context, which fits in 8 GB VRAM with room for other processes.

Does the model support image inputs in llama.cpp?

Currently, llama.cpp does not accept image input on the embedding endpoint for this architecture; image support is planned for a future release.

What license applies to this model?

The model is governed by the OpenMDW License 1.1, which applies to all GGUF conversions.

Other GGUFs of Nemotron-3.5-Embed-1B-BF16

Similar models

Browse all →

More from W4D

All by W4D →

More Nemotron models

All Nemotron →

Other tiny models

All tiny models →