Uncensored
Cognitive Computations · released Jun 12, 2025 · cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition
- Type
- Open weightsApache License 2.0
- Params
- 24B
- Context
- 128K
about 96K words of context
Our take
Written Aug 2, 2026Uncensored is a 24-billion-parameter text model from Cognitive Computations with a permissive Apache licence and a 128,000-token request limit. It is positioned for generation without content restrictions, though no quality scores are available to measure its capabilities.
Pick this when uncensored output is the priority and you need a permissive licence that allows commercial use, modification and redistribution. Use it for long-document work with its 128,000-token request limit, or for low-cost hosted inference where both tracked providers charge the same rate. Skip it if you need measured quality data, verified throughput on every host, or clarity on whether the full context length remains usable throughout.
The case for it
- Apache License 2.0 allows commercial use, modification and redistribution without restriction.
- Identical pricing across both tracked providers, with one adding 64 tokens per second throughput at no premium.
The case against it
- No benchmark scores in our data: chat, reasoning, coding and safety evaluations are all absent.
- Throughput is unverified on one of two offers, with only Venice disclosing a measured figure.
- Active parameter count is undisclosed, so efficiency claims about the architecture remain unverified.
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 Uncensored — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
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
GeForce RTX 4090 · 24 GB
Room to spare. 5.7 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 13.7 GB spare means a 10% error in the size would not change the answer.
Apple M2 (10-core GPU) · 24 GB
Borderline fit on an estimated size. It leaves 0.9 GB spare on a size we calculated rather than measured, and a 10% error either way would change the answer.
Memory use by level
Against a 24 GB card.
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 →
Or rent it from someone else
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
- $0.20 in / $0.90 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.20 / $0.90 | 128K | not measured | Unknown | Unknown | Unknown |
| Venice AIfp16 | $0.20 / $0.90 | 128K | 83 tok/s | No | No | Confirmed |
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
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✗ |
| Venice AIfp16 | ✗ | ✓ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Dates behind this page
Prices last checked 6h 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.
Licence and identifiers
What the licence allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Architecture
- Dense
- Modality record
- text->text
- Catalogue slug
- cognitivecomputations-uncensored