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 Aug 1, 2026TheDrummer is a 36.9-billion-parameter text-only model released in early 2025 with downloadable weights under a custom licence. It handles up to 32,768 tokens in a single request, but with only two hosting options and no measured quality scores, it is a narrow-use pick rather than a general-purpose workhorse.
Choose this for budget-constrained text-only workloads where the custom licence terms are acceptable, or when Parasail's 22 tokens per second meets your latency needs. Skip it if you need measured quality benchmarks, want a standard permissive licence like Apache or MIT, or require provider redundancy and geographic choice.
The case for it
- Identical pricing across both providers eliminates cost-based provider switching.
- 36.9 billion parameters places it in the capable mid-size range for text tasks.
The case against it
- No measured quality or capability scores in our data — no Elo, MMLU, coding, or reasoning scores available.
- Throughput data is thin and partially missing: only one of two providers reports speed, the other is unverified in our data.
- Custom licence and small provider footprint create friction versus standard alternatives.
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 Skyfall 36B V2 — 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%
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.
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.
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
- $0.55 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 |
|---|---|---|---|---|---|---|
| OpenRouter | $0.55 / $0.80 | 33K | not measured | Unknown | Unknown | Unknown |
| Parasailfp8 | $0.55 / $0.80 | 33K | 53 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 | ✗ | ✓ | ✓ |
| Parasailfp8 | ✗ | ✓ | ✓ |
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
Dates behind this page
Prices last checked 35h 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.
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
- Modality record
- text->text
- Catalogue slug
- thedrummer-skyfall-36b-v2