How much VRAM does nomic-embed-text v1.5 need?

nomic-embed-text v1.5 requires 410 MB VRAM at recommended quality (Q8_0). At lower quality settings, it can fit in as little as 410 MB.

What is the best GPU for nomic-embed-text v1.5?

The NVIDIA GeForce RTX 4070 Ti 12GB delivers the best performance for nomic-embed-text v1.5, achieving 6500 tok/s at Q8_0 with an excellent rating.

What quantization should I use for nomic-embed-text v1.5?

For the best quality, use Q8_0 (410 MB VRAM). If your GPU has limited VRAM, Q8_0 (410 MB) is the most efficient option with acceptable quality.

EmbeddingsAI building137M

Embeddings

nomic-embed-text v1.5

Nomic · Apache 2.0

High-quality text embedding model for RAG pipelines. 137M params, negligible VRAM. Competitive with OpenAI's ada-002 on MTEB benchmarks. Essential for builders running local RAG with Cursor or similar tools. Can run concurrently with coding models without meaningful VRAM impact.

Parameters: 137M
Architecture: Dense
Context: 8,192 tokens
Released: 2024-02-02
Engines: ollama, llama.cpp
Builder Tools: Cursor, Continue, AnythingLLM, Open WebUI

Parameters

137M

VRAM

410 MB

Context

Formats

GPUs

nomic-embed-text v1.5 (137M) requires 410 MB VRAM at recommended quality (Q8_0). On NVIDIA GeForce RTX 4070 Ti 12GB, expect approximately 6500 tok/s at Q8_0. For the best experience, Starter AI Desktop ($582) is recommended.

Source: OwnRig methodology

VRAM (Recommended)

410 MB

Quantization

Q8_0

File Size

0.14 GB

Max Context

8K tokens

Primary Use

Embeddings

Memory

VRAM Requirements

Quality	Quantization	VRAM	File Size
full	FP16	512 MB	0.27 GB
recommended	Q8_0	410 MB	0.14 GB

Scaling

Context Length Impact

KV cache VRAM at Q8_0 quality. Longer context = more memory.

Context	KV Cache	Total VRAM
2K	0 MB	410 MB
4K	0 MB	410 MB
8K	102 MB	512 MB

Compatible GPUs

22 devices


NVIDIA Grace Blackwell Ultra GB300	FP16	2000 tok/s	Excellent
Apple M4 Max (64GB Unified)	FP16	–	Excellent
Apple M4 Pro (48GB)	FP16	–	Excellent
NVIDIA GeForce RTX 3060 12GB	FP16	–	Excellent
NVIDIA GeForce RTX 3080 10GB	Q8_0	2500 tok/s	Excellent
NVIDIA GeForce RTX 4060 8GB	Q8_0	4200 tok/s	Excellent
NVIDIA RTX 4060 Laptop (40-60W)	Q8_0	2520 tok/s	Excellent
NVIDIA RTX 4070 Laptop (80-115W)	Q8_0	2940 tok/s	Excellent
NVIDIA GeForce RTX 4070 Super	FP16	–	Excellent
NVIDIA GeForce RTX 4070 Ti 12GB	Q8_0	6500 tok/s	Excellent
NVIDIA RTX 4080 Laptop (120-150W)	Q8_0	4550 tok/s	Excellent
NVIDIA GeForce RTX 4090	FP16	–	Excellent
AMD Radeon Pro W7900	FP16	–	Excellent
NVIDIA RTX PRO 6000 Blackwell	FP16	2000 tok/s	Excellent
NVIDIA RTX PRO 6000 Blackwell Max-Q	FP16	1840 tok/s	Excellent
NVIDIA GeForce RTX 5060 8GB	Q8_0	4830 tok/s	Excellent
Apple M3 Pro (18GB Unified)	Q8_0	600 tok/s	Good
AMD Radeon RX 7600	Q8_0	500 tok/s	Good
AMD Radeon RX 7900 XTX	FP16	–	Good
AMD Radeon RX 9070	FP16	–	Acceptable
AMD Radeon RX 9060 XT 16GB	FP16	–	Acceptable
AMD Radeon RX 9060 XT 8GB	FP16	–	Acceptable

Showing 22 of 22 entries

Builder Context

nomic-embed-text v1.5 is commonly used with Cursor, Continue, AnythingLLM, Open WebUI.

Hardware

Recommended Builds

Complete PC builds that can run nomic-embed-text v1.5.

Mid-range

AI Builder Workstation

Run every AI tool you need. Nothing leaves your machine

RTX 4090·24 GBVRAM

Runs 10 models

$2,773

Budget

Budget AI Desktop

Your own AI coding setup for under $800

RTX 3060 12GB·12 GBVRAM

Runs 7 models

$684

Budget

Budget Home AI Server

Always-on AI assistant for the whole household

RTX 4060 Ti 16GB·16 GBVRAM

Runs 7 models

$1,063

Mid-range

Compact SFF AI Build

Serious AI power in a compact, desk-friendly form factor

RTX 4070 Super 12GB·12 GBVRAM

Runs 5 models

$1,304

High-end

High-End Home AI Server

Your household's private AI: chatbots, code tools, and more

2x NVIDIA GeForce RTX 3090 24GB (Used) + NVLink Bridge·48 GBVRAM

Runs 12 models

$3,623

High-end

Mac Studio AI Builder

Plug in and run AI: silent, powerful, no assembly required

M4 Max 128GB (Mac Studio)·128 GBVRAM

Runs 6 models

$3,999

Mid-range

Mid-Range AI Workstation

The sweet spot for AI: handles most models without overspending

RTX 4060 Ti 16GB·16 GBVRAM

Runs 8 models

$1,119

Mid-range

Mid-Range Home AI Server

Serve multiple AI models to every device at home

RTX 3090 24GB (Used)·24 GBVRAM

Runs 9 models

$1,773

Mid-range

Silent Mini-ITX AI Box

Whisper-quiet AI processing for noise-sensitive environments

RTX 4060 Ti 16GB·16 GBVRAM

Runs 8 models

$1,114

FAQ

Frequently Asked Questions

How much VRAM does nomic-embed-text v1.5 need?: nomic-embed-text v1.5 requires 410 MB VRAM at recommended quality (Q8_0). At lower quality settings, it can fit in as little as 410 MB.
What is the best GPU for nomic-embed-text v1.5?: The NVIDIA GeForce RTX 4070 Ti 12GB delivers the best performance for nomic-embed-text v1.5, achieving 6500 tok/s at Q8_0 with an excellent rating.
What quantization should I use for nomic-embed-text v1.5?: For the best quality, use Q8_0 (410 MB VRAM). If your GPU has limited VRAM, Q8_0 (410 MB) is the most efficient option with acceptable quality.

All models

Data confidence: verified. Source

VRAM requirements are calculated from model parameters and may vary by inference engine, context length, and batch size. Performance estimates are based on community benchmarks and should be verified for your specific configuration.Nomic is a trademark of its respective owner. OwnRig is not affiliated with or endorsed by the model creator.