Models / Reka AI/ Reka Edge

Reka Edge

Reka AI · released Mar 11, 2026 · RekaAI/reka-edge-2603

Input: text, images and video. Output: text.InputOutput
Type
Open weightsCustom licence
Params
7.1B
Context
16K

about 12K words of context · download allowed, licence restricts use

Our take

Written Aug 3, 2026

Reka Edge is a compact multimodal model that accepts text, images and video on a small parameter budget. It is positioned as a lightweight, cost-sensitive option for teams that need vision inputs without a large footprint.

Who should pick it

Pick this when you need multimodal inputs at minimal cost and can accept unverified quality. Use it for constrained environments where a 7.1-billion-parameter model fits. Skip it if you need measured benchmark scores, high throughput, a standard permissive licence, or a context window above sixteen thousand tokens.

The case for it

  • Extremely cheap multimodal access: both tracked providers charge the same low rate for input and output.
  • Handles text, images and video at a small scale unusual for multimodal models.

The case against it

  • No measured quality in our data: chat, reasoning, coding and vision performance are all unverified.
  • Very low throughput on native hosting, at five tokens per second.
  • Custom restricted licence and a narrow sixteen-thousand-token context window, with no larger option listed.
00

How good is it?

We hold no score for this model.

We look for every model we track on every board we watch, and none of them has turned up Reka Edge — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.

The boards we watch →

01

Can you run it yourself?

Fits in memory
weights load entirely on the card
Spills to system RAM
some weights offload; much slower
Too large
will not load even with offload
est
size is calculated; the verdict could change by 10%

Comfortable fit

A card many people ownFits in memory

GeForce RTX 4090 · 24 GB

Weights at Q4_K_M4.5 / 24 GBest
Spare memory16.7 GB spare
Usable context16K of 16K
Decode speed187 tok/sest

Room to spare. 16.7 GB spare means a 10% error in the size would not change the answer.

One step upFits in memory

GeForce RTX 5090 · 32 GB

Weights at Q4_K_M4.5 / 32 GBest
Spare memory24.7 GB spare
Usable context16K of 16K
Decode speed333 tok/sest

Room to spare. 24.7 GB spare means a 10% error in the size would not change the answer.

On a MacFits in memory

Apple M1 (8-core GPU) · 16 GB

Weights at Q4_K_M4.5 / 16 GBest
Spare memory5.9 GB spare
Usable context16K of 16K
Decode speed11 tok/sest

Room to spare. 5.9 GB spare means a 10% error in the size would not change the answer.

Your hardware
Checking your profile…

Memory use by level

Against a 24 GB card.

Q4_K_M
recommended
4.5 GBest
Fits in memory
Q5_K_M
5.3 GBest
Fits in memory
Q8_0
7.9 GBest
Fits in memory

All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.

Check against your own machine → · All 71 devices, with every size →

02

Or rent it from someone else

Cheapest published offer

Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.

per 1M tokens
$0.10 in / $0.10 out
Context served
16K
Throughput
Not measured
Current provider offers with price, context and prompt-privacy answers
ProviderIn / out per 1M tokensContextThroughputTrains on promptsLogs promptsZero retention
OpenRouter$0.10 / $0.1016Knot measuredUnknownUnknownUnknown
Rekabf16$0.10 / $0.1016K3 tok/sNoNoConfirmed

Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 1 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.

What each host's API supports

From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.

Supported
Not supported
Not published
host gave no parameter list
API features per host
ProviderTool callingJSON outputStrict schema
OpenRouter
Rekabf16

Tool calling: 2 of 2 listings say yes. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 2 of 2 listings say yes.

03

When we formed this view

Dates behind this page

Jul 26, 2026ListedListed on LLMapfirst indexed by our pipeline
Mar 11, 2026AnnouncedReka Edge announced by Reka AI

Prices last checked 14h ago

What we do not know about this model yet

  • We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
  • No board we watch has turned up a score, so we hold no quality figures at all.
  • Nothing we hold says whether an endpoint streams, so we do not show it either way.
  • 1 of 2 listings do not say whether they train on prompts.
  • We hold no cached-input rate for any of its listings.
04

Licence and identifiers

What the licence allowsCustom licence, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.

Licence

Custom licence

restricted_openCustom licence — review the terms

This model ships custom license terms that don't map to a known template. We haven't parsed them, so commercial use, redistribution and derivatives are unverified — review the original terms before shipping.

Identifiers

Architecture
Dense
Modality record
text+image+video->text
Catalogue slug
rekaai-reka-edge

Machine-readable model card (omc.json) →

Something wrong on this page? Tell us