Perplexity · Embeddings and rerank · 8.4B parameters · MIT
pplx-embed-v2-context-9b-preview
Needs 11 GB at FP8 / INT8. The smallest real configuration today is 1× RTX 3060 at Vast.ai, $0.04 per hour, about $26 a month at 730 hours.
Parameters8.4Bdense
Context256k tokensmaximum published
Checkpoint34 GBFP32, as published
LicenseMITcheck before commercial use
ReleasedSep 25, 2026documented date
Smallest configuration · FP8 / INT8
1× RTX 306012 GB VRAM · 84% used
- Per hour
- $0.04
- Per month
- $26
- Cheapest at
Vast.ai
What is documented about pplx-embed-v2-context-9b-preview
news checked 2026-10-27Contextual chunk embeddings for RAG (whole document encoded, one embedding per chunk); 2048-d with MRL 1024; native int8 unnormalized outputs. Explicitly a preview: embeddings may not be compatible with the final release. Date = HF repo creation.
- https://huggingface.co/perplexity-ai/pplx-embed-v2-context-9b-preview
- https://huggingface.co/api/models/perplexity-ai/pplx-embed-v2-context-9b-preview?blobs=true
Memory · 3 precisions · 5 context lengthsHow much VRAM it needs
Weights plus runtime overhead, then the KV cache that grows with the context you serve.
| Precision | Weights | Weights + headroom | 4k context | 32k context | 128k context | 256k context |
|---|---|---|---|---|---|---|
| FP32published checkpoint | 34 GB | 41 GB | 41 GB | 45 GB | 58 GB | 75 GB |
| FP8 / INT8estimated | 8 GB | 11 GB | 11 GB | 15 GB | 28 GB | 45 GB |
| INT4 / MXFP4estimated | 5 GB | 7 GB | 7 GB | 11 GB | 24 GB | 41 GB |
| KV cacheone sequence, FP16 cache, included above | — | — | 1 GB | 5 GB | 18 GB | 35 GB |
Cross-checked on Hugging Face Oct 28, 2026: 8.40B parameters in the safetensors headers, 33.6 GB of weight files, attention layout from config.json (32 layers, 4 KV heads × 256). Method: weights as published at the native precision, verified on Hugging Face 2026-10-28; other precisions estimated at 1 (8-bit) and 0.6 (4-bit) bytes per parameter; × 1.2 runtime headroom; KV cache = 4096 bytes per token per layer × 32 full-attention layers (FP16 cache, one sequence).config.json ↗
Smallest configuration per GPU · 109 GPUs · cheapest eligible on-demand offer per GPU count, every provider on fileWhat it costs to run, GPU by GPU
The fewest GPUs of one type whose total memory fits the model at short context, priced from the cheapest eligible on-demand offer for exactly that count (45-day window, newest reading per provider), with the next providers beside it. Monthly = 730 hours.
| GPU | Smallest config | VRAM used | $ / hour | $ / month | Cheapest at |
|---|---|---|---|---|---|
| RTX 3060Best fit | 1× 12 GB12 GB total | 84% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.05, gcube $0.05 |
| RTX A2000 | 1× 12 GB12 GB total | 84% | $0.04 | $26 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.09, Runpod $0.12 |
| T4 | 1× 16 GB16 GB total | 63% | $0.04 | $29 | Vast.aiTrust 78 · read Nov 2 · receipt · also iwinv $0.20, Theta EdgeCloud $0.20 |
| Tesla P40 | 1× 24 GB24 GB total | 42% | $0.04 | $30 |  Clore.aiTrust 49 · read Nov 2 · receipt · also gcube $0.07, Vast.ai $0.11 |
| GTX Titan X | 1× 12 GB12 GB total | 84% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Titan Xp | 1× 12 GB12 GB total | 84% | $0.04 | $31 | Vast.aiTrust 78 · read Nov 2 · receipt |
| Tesla P100 | 1× 16 GB16 GB total | 63% | $0.04 | $33 | Vast.aiTrust 78 · read Nov 2 · receipt · also gcube $0.07 |
| Tesla V100 16GB | 1× 16 GB16 GB total | 63% | $0.06 | $46 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.08, CloudRift $0.28 |
| GTX 1080 Ti | 1× 11 GB11 GB total | 92% tight | $0.06 | $47 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.08 |
| RTX 2080 Ti | 1× 11 GB11 GB total | 92% tight | $0.07 | $49 | |
| Tesla V100 32GB | 1× 32 GB32 GB total | 32% | $0.07 | $50 | Vast.aiTrust 78 · read Nov 2 · receipt · also Cyfuture AI $0.57, E2E Networks $1.50 |
| RTX PRO 2000 | 1× 16 GB16 GB total | 63% | $0.07 | $51 | Clore.aiTrust 49 · read Nov 2 · receipt · also gcube $0.16 |
| RTX A4000 | 1× 16 GB16 GB total | 63% | $0.07 | $53 | Vast.aiTrust 78 · read Nov 2 · receipt · also Edgevana $0.10, gcube $0.10 |
| Tesla M40 | 1× 24 GB24 GB total | 42% | $0.07 | $54 | Clore.aiTrust 49 · read Nov 2 · receipt · also gcube $0.07 |
| RTX 3060 Ti | 2× 8 GB16 GB total | 63% | $0.08 | $61 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.12, AtmosCompute $0.34 |
| RTX 5060 Ti | 1× 16 GB16 GB total | 63% | $0.08 | $61 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.09, Theta EdgeCloud $0.12 |
| RTX 4070 | 1× 12 GB12 GB total | 84% | $0.08 | $61 | Clore.aiTrust 49 · read Nov 2 · receipt · also Vast.ai $0.11, gcube $0.14 |
| GTX 1660 | 2× 6 GB12 GB total | 84% | $0.09 | $64 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 3090 | 1× 24 GB24 GB total | 42% | $0.09 | $66 | |
| RTX 4070 Super | 1× 12 GB12 GB total | 84% | $0.10 | $70 | Vast.aiTrust 78 · read Nov 2 · receipt · also Clore.ai $0.13, gcube $0.15 |
| GTX 1070 | 2× 8 GB16 GB total | 63% | $0.10 | $70 | Vast.aiTrust 78 · read Nov 2 · receipt |
| GTX 1080 | 2× 8 GB16 GB total | 63% | $0.10 | $76 | Vast.aiTrust 78 · read Nov 2 · receipt |
| RTX 3080 Ti | 1× 12 GB12 GB total | 84% | $0.10 | $76 | Clore.aiTrust 49 · read Nov 2 · receipt · also gcube $0.10, Vast.ai $0.11 |
| L4 | 1× 24 GB24 GB total | 42% | $0.10 | $76 | Vast.aiTrust 78 · read Nov 2 · receipt · also Hikube $0.27, Infomaniak $0.28 |
| The 24 cheapest of 99 GPU types that fit. Every GPU, any precision and context, in the finder | |||||
pplx-embed-v2-context-9b-preview · related