🧠

Model

Pplx Embed V1 4b Mlx

Name: Pplx Embed V1 4b Mlx
Author: agentmish

by agentmish hf-model--agentmish--pplx-embed-v1-4b-mlx

Nexus Index

39.9 Top 100%

S: Semantic 50

A: Authority 0

P: Popularity 14

R: Recency 99

Q: Quality 65

Tech Context

4 Params

4.096K Ctx

Vital Performance

305 DL / 30D

0.0%

Source →

Audited 39.9 FNI Score

4B Params

4k Context

305 Downloads

8G GPU ~5GB Est. VRAM

Commercial MIT License

Model Information Summary
Entity Passport
Registry ID	hf-model--agentmish--pplx-embed-v1-4b-mlx
License	MIT
Provider	huggingface

💾

Compute Threshold

~4.3GB VRAM

Interactive

Analyze Hardware

Hardware Compatibility Test

▼

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX

@misc{hf_model__agentmish__pplx_embed_v1_4b_mlx,
  author = {agentmish},
  title = {Pplx Embed V1 4b Mlx Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/agentmish/pplx-embed-v1-4b-mlx}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}

APA Style

agentmish. (2026). Pplx Embed V1 4b Mlx [Model]. Free2AITools. https://huggingface.co/agentmish/pplx-embed-v1-4b-mlx

🔬Technical Deep Dive

Full Specifications [+]

Quick Commands

🦙 Ollama Run

ollama run pplx-embed-v1-4b-mlx

🤗 HF Download

huggingface-cli download agentmish/pplx-embed-v1-4b-mlx

📦 Install Lib

pip install -U transformers

⚖️ Nexus Index V2.0

Methodology Index Protocol

39.9

TOP 100% SYSTEM IMPACT

Semantic (S) 50

Authority (A) 0

Popularity (P) 14

Recency (R) 99

Quality (Q) 65

💬 Index Insight

FNI V2.0 for Pplx Embed V1 4b Mlx: Semantic (S:50), Authority (A:0), Popularity (P:14), Recency (R:99), Quality (Q:65).

Free2AITools Nexus Index

Verification Authority

HuggingFace API GitHub Metadata Arxiv Citation DB System Audit

Unbiased Data Node Refresh: VFS Live

---

🚀 What's Next?

📊

Find Training Datasets

Discover datasets compatible with this model

📈

Compare Benchmarks

See how this model ranks on standard tests

⚡

Technical Deep Dive

pplx-embed-v1: Diffusion-Pretrained Dense and Contextual Embeddings

pplx-embed-v1 and pplx-embed-context-v1 are state-of-the-art text embedding models optimized for real-world, web-scale retrieval tasks.

Use pplx-embed-v1 for independent text embedding (queries, documents, semantic search)
Use pplx-embed-context-v1 for document chunks in RAG systems where surrounding context matters

[!IMPORTANT] pplx-embed-v1 and pplx-embed-context-v1 natively produce unnormalized int8-quantized embeddings. Ensure that you compare them via cosine similarity.

Models

Model	Dimensions	Context	MRL	Quantization	Instruction	Pooling
`pplx-embed-v1-0.6B`	1024	32K	Yes	INT8/BINARY	No	Mean
`pplx-embed-v1-4B`	2560	32K	Yes	INT8/BINARY	No	Mean
`pplx-embed-context-v1-0.6B`	1024	32K	Yes	INT8/BINARY	No	Mean
`pplx-embed-context-v1-4B`	2560	32K	Yes	INT8/BINARY	No	Mean

_{All models are built on diffusion continued pre-trained Qwen3 at Perplexity AI.}

_{Many modern embedding models rely on instruction tuning, where users prepend an instruction string to the text being embedded. This can yield a 2%-3% lift on benchmarks, but it also introduces prompt-selection overhead and can make indexing pipelines brittle (small instruction changes can shift embedding space). We deliberately avoid this requirement: you can embed the text you want to index directly, without having to choose or maintain an instruction prefix.}

Usage

Via API

bash

curl -X POST https://api.perplexity.ai/v1/embeddings \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": [
      "Scientists explore the universe driven by curiosity.",
      "Children learn through curious exploration.",
      "Historical discoveries began with curious questions.",
      "Animals use curiosity to adapt and survive.",
      "Philosophy examines the nature of curiosity."
    ],
    "model": "pplx-embed-v1-4b"
  }'

Using SentenceTransformers

python

from sentence_transformers import SentenceTransformer

model = SentenceTransformer(
    "perplexity-ai/pplx-embed-v1-4B",
    trust_remote_code=True
)

texts = [
    "Scientists explore the universe driven by curiosity.",
    "Children learn through curious exploration.",
    "Historical discoveries began with curious questions.",
    "Animals use curiosity to adapt and survive.",
    "Philosophy examines the nature of curiosity.",
]

embeddings = model.encode(texts) # Shape: (5, 2560), quantized to int8
embeddings = model.encode(texts, quantization="binary") # Shape: (5, 2560), quantized to binary

Using ONNX models

python


import onnxruntime as ort
from transformers import AutoTokenizer
import numpy as np

tokenizer = AutoTokenizer.from_pretrained("perplexity-ai/pplx-embed-v1-4b", trust_remote_code=True)
session = ort.InferenceSession("onnx/model.onnx")


texts = [
    "Scientists explore the universe driven by curiosity.",
    "Children learn through curious exploration.",
    "Historical discoveries began with curious questions.",
    "Animals use curiosity to adapt and survive.",
    "Philosophy examines the nature of curiosity.",
]

tokenized = tokenizer(
    texts,
    padding=True,
    truncation=True,
    return_tensors="np"
)

onnx_inputs = {
    "input_ids": tokenized["input_ids"].astype(np.int64),
    "attention_mask": tokenized["attention_mask"].astype(np.int64),
}

# Run inference
onnx_embeddings = session.run([out.name for out in session.get_outputs()], onnx_inputs)

# ONNX produces both int8 and binary precision embeddings:
int8_embeddings = onnx_embeddings[2]
binary_embeddings = onnx_embeddings[3]
packed_embeddings = np.packbits(binary_embeddings != -1, axis=-1)

Using Text Embeddings Inference (TEI)

[!NOTE] Text Embeddings Inference v1.9.2+ is required.

[!IMPORTANT] Currently, only int8-quantized embeddings are available via TEI. Remember to use cosine similarity with unnormalized int8 embeddings.

CPU w/ Candle:

bash

docker run -p 8080:80 ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 --model-id perplexity-ai/pplx-embed-v1-4B --dtype float32

CPU w/ ORT (ONNX Runtime):

bash

docker run -p 8080:80 ghcr.io/huggingface/text-embeddings-inference:cpu-1.9 --model-id onnx-community/pplx-embed-v1-4B --dtype float32

GPU w/ CUDA:

bash

docker run --gpus all --shm-size 1g -p 8080:80 ghcr.io/huggingface/text-embeddings-inference:cuda-1.9 --model-id perplexity-ai/pplx-embed-v1-4B --dtype float32

If you hit OOM during warmup, lower --max-batch-tokens and --max-client-batch-size. Set --max-batch-tokens to max_sequence_length × batch_size (e.g., 2048 tokens × 8 sequences = 16384).

Alternatively, when running in CUDA you can use the architecture / compute capability specific container instead of the cuda-1.9, as that includes the binaries for Turing, Ampere, Hopper and Blackwell, so using a dedicated container will be lighter e.g., ampere-1.9.

And then you can send requests to it via cURL to /embed:

bash

curl http://0.0.0.0:8080/embed \
  -H "Content-Type: application/json" \
  -d '{
    "inputs": [
      "Scientists explore the universe driven by curiosity.",
      "Children learn through curious exploration.",
      "Historical discoveries began with curious questions.",
      "Animals use curiosity to adapt and survive.",
      "Philosophy examines the nature of curiosity."
    ],
    "normalize": false
  }'

Technical Details

For comprehensive technical details and evaluation results, see our paper on arXiv: https://arxiv.org/abs/2602.11151.

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

• Benchmark scores may vary based on evaluation methodology and hardware configuration.
• VRAM requirements are estimates; actual usage depends on quantization and batch size.
• FNI scores are relative rankings and may change as new models are added.
⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub

305Downloads

Hub Discussions

🤗 Data Source: Hugging Face ↗

🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: hf-model--agentmish--pplx-embed-v1-4b-mlx
slug: agentmish--pplx-embed-v1-4b-mlx
source: huggingface
author: agentmish
license: MIT
tags: sentence-transformers, safetensors, qwen3, feature-extraction, sentence-similarity, mteb, custom_code, multilingual, arxiv:2602.11151, license:mit, text-embeddings-inference, endpoints_compatible, region:us, mlx, bidirectional_pplx_qwen3, apple-silicon, perplexity, base_model:perplexity-ai/pplx-embed-v1-4b

⚙️ Technical Specs

architecture: null
params billions: 4
context length: 4,096
pipeline tag: feature-extraction
vram gb: 4.3
vram is estimated: true
vram formula: VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads: 305
stars: 0
forks: 0

Data indexed from public sources. Updated daily.

Welcome to Free2AI Tools!

Smart Search

FNI Score

You're All Set!

Cite this model

🔬Technical Deep Dive

Quick Commands

⚖️ Nexus Index V2.0

💬 Index Insight

Verification Authority

🚀 What's Next?

Find Training Datasets

Compare Benchmarks

Deployment Guide

Technical Deep Dive

Models

Usage

Technical Details

⚠️ Incomplete Data

📝 Limitations & Considerations

Social Proof

🛡️ Model Transparency Report

🆔 Identity & Source

⚙️ Technical Specs

📊 Engagement & Metrics