EmbeddingsAI Building137M
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
- Context
- 8,192 tokens
- Released
- 2024-02-02
- Engines
- ollama, llama.cpp
- Builder Tools
- Cursor, Continue, AnythingLLM, Open WebUI
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.
— OwnRig methodology, data updated 2026-03-01
VRAM Requirements
| Quality | Quantization | VRAM | File Size |
|---|---|---|---|
| full | FP16 | 512 MB | 0.27 GB |
| recommended | Q8_0 | 410 MB | 0.14 GB |
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
Performance data for nomic-embed-text v1.5 across different hardware.
| Device | Quantization | Speed | Rating | Fits in VRAM |
|---|---|---|---|---|
| NVIDIA GeForce RTX 3060 12GB | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4090 | FP16 | — | Excellent | ✓ |
| Apple M4 Max (64GB Unified) | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4070 Super | FP16 | — | Excellent | ✓ |
| Apple M4 Pro (48GB) | FP16 | — | Excellent | ✓ |
| NVIDIA GeForce RTX 4060 8GB | Q8_0 | 4200 tok/s | Excellent | ✓ |
| NVIDIA GeForce RTX 4070 Ti 12GB | Q8_0 | 6500 tok/s | Excellent | ✓ |
| NVIDIA GeForce RTX 3080 10GB | Q8_0 | 2500 tok/s | Excellent | ✓ |
| Apple M3 Pro (18GB Unified) | Q8_0 | 600 tok/s | Good | ✓ |
Builder Context
nomic-embed-text v1.5 is commonly used with Cursor, Continue, AnythingLLM, Open WebUI.
Recommended Builds
Complete PC builds that can run nomic-embed-text v1.5.
Mid-Range
Budget
Budget
Mid-Range
High-End
High-End
Mid-RangeMid-RangeMid-Range
Mid-RangeFull AI Builder
AI Builder Workstation
NVIDIA GeForce RTX 4090 · 64GB DDR5-5600 (2x32GB)
$2,90224 GB VRAM
Runs 10 models
BudgetBasic AI Coding
Budget AI Desktop
NVIDIA GeForce RTX 3060 12GB · 32GB DDR4-3200 (2x16GB)
$75312 GB VRAM
Runs 7 models
BudgetHome AI Server
Budget Home AI Server
NVIDIA GeForce RTX 4060 Ti 16GB · 32GB DDR5-5200 (2x16GB)
$1,16216 GB VRAM
Runs 7 models
Mid-RangeBasic AI Coding
Compact SFF AI Build
NVIDIA GeForce RTX 4070 Super 12GB · 32GB DDR5-5600 (2x16GB)
$1,47312 GB VRAM
Runs 5 models
High-EndHome AI Server
High-End Home AI Server
2x NVIDIA GeForce RTX 3090 24GB (Used) + NVLink Bridge · 128GB DDR5-5600 (4x32GB)
$3,84248 GB VRAM
Runs 12 models
High-EndFull AI Builder
Mac Studio AI Builder
Apple M4 Max 128GB (Mac Studio)
$3,999128 GB VRAM
Runs 6 models
Mid-RangePower AI Coding
Mid-Range AI Workstation
NVIDIA GeForce RTX 4060 Ti 16GB · 32GB DDR5-5600 (2x16GB)
$1,22816 GB VRAM
Runs 8 models
Mid-RangeHome AI Server
Mid-Range Home AI Server
NVIDIA GeForce RTX 3090 24GB (Used) · 64GB DDR5-5600 (2x32GB)
$1,89224 GB VRAM
Runs 9 models
Mid-RangeHome AI Server
Silent Mini-ITX AI Box
NVIDIA GeForce RTX 4060 Ti 16GB · 32GB DDR5-5600 (2x16GB)
$1,25316 GB VRAM
Runs 8 models
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.
Data confidence: verified. Last updated: 2026-03-01. Source