Skyfall 36B V2
TheDrummer · released Feb 3, 2025 · TheDrummer/Skyfall-36B-v2
- Type
- Open weightsCustom licence
- Params
- 36.9B
- Context
- 33K
about 25K words of context · download allowed, licence restricts use
Our take
Written Sep 12, 2026Skyfall 36B V2 is a 36.9-billion-parameter text-only model from TheDrummer with a 32,768-token request limit and a restricted custom licence. It is a mid-size downloadable option with only two tracked hosts and no measured quality data yet.
Pick this when you need a 32K-context text model at moderate scale and the restricted licence does not block your use case. Consider it if Parasail's 51 tokens per second meets your latency needs. Skip it if you require measured quality benchmarks, a permissive licence, or competitive pricing between providers.
The case for it
- 36.9 billion parameters, a moderate scale in a field where larger is increasingly common.
- Two hosted offers available, including Parasail at 51 tokens per second throughput.
The case against it
- No benchmark scores in our data, so there is no measured quality to validate performance claims.
- Custom restricted licence, less commercially flexible than Apache or MIT alternatives.
- Only two tracked offers at identical pricing, so provider competition is limited.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
GeForce RTX 4090 · 24 GB
Loads, but do not expect an assistant. Some of the weights sit in ordinary system memory, which is far slower than the card.23.3 GB of weights, plus 2.4 GB for the software that runs it and the smallest conversation it can hold, comes to 25.7 GB against the 22.8 GB this 24 GB device leaves free.
Comfortable fit
GeForce RTX 5090 · 32 GB
Room to spare. 5.1 GB spare means a 10% error in the size would not change the answer.
Apple M3 Pro (18-core GPU) · 36 GB
Borderline fit on an estimated size. It leaves 1.3 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.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.55 in / $0.80 out
- Context served
- 33K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.55 / $0.80checked 4 hours ago | 33K | not measured | Unknown | Unknown | Unknown |
| Parasailfp8Through OpenRouter | $0.55 / $0.80checked 4 hours ago | 33K29K max reply | 55 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✓ | ✓ |
| Parasailfp8Through OpenRouter | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 independent board has scored it, 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 does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
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
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
- Hugging Face
- TheDrummer/Skyfall-36B-v2
- Architecture
- Dense
- Takes in, gives back
- Text in, text out
- Catalogue slug
- thedrummer-skyfall-36b-v2