Skyfall 36B V2
Summary
Skyfall 36B V2 is an open-weight language model from Thedrummer, released on 10 Mar 2025. It accepts text and generates text, with a 33K-token context window and up to 29K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $0.55 per million input tokens and $0.80 per million output tokens (OpenRouter), across 1 provider we track.
Open-weight instruction model for adaptable chat and self-hosted production workloads
Last verified 19 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Thedrummer |
|---|---|
| Release date | 10 Mar 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| Parameters | 36.9B [Hugging Face] |
| Context window | 33K (32,768 tokens) [models.dev] |
| Max output | 29K tokens [models.dev] |
| Knowledge cutoff | 30 Jun 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | TheDrummer/Skyfall-36B-v2 [Hugging Face] |
Skyfall 36B V2 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter thedrummer/skyfall-36b-v2 | $0.55 | $0.80 | $0.25 | 33K | OpenRouter, 19 Nov 2026 |
Running Skyfall 36B V2 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 22 GB | 25 GB | 32 GB |
| Q8_0 (8-bit) | 39 GB | 42 GB | 49 GB |
| FP16 / BF16 (16-bit) | 74 GB | 77 GB | 83 GB |
At 4-bit with an 8K conversation, Skyfall 36B V2 needs about 25 GB, so it fits on a graphics card with 32 GB or more, such as the NVIDIA GeForce RTX 5090 32 GB. Check your own hardware, or see Best GPU for local LLMs on our sister site AIPCs.
Frequently asked questions
What is the context window of Skyfall 36B V2?
Skyfall 36B V2 has a context window of 32,768 tokens (33K) and can generate up to 29,491 tokens in a single response, according to models.dev.
How much does the Skyfall 36B V2 API cost?
Skyfall 36B V2 is listed from $0.55 per million input tokens and $0.80 per million output tokens (OpenRouter). Prices last verified 19 Nov 2026.
Is Skyfall 36B V2 open source?
Skyfall 36B V2 is an open-weight model: its weights are published on Hugging Face as TheDrummer/Skyfall-36B-v2. Check the license terms before commercial use.
When was Skyfall 36B V2 released?
Thedrummer released Skyfall 36B V2 on 10 Mar 2025, according to models.dev.
How much VRAM does Skyfall 36B V2 need?
About 25 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 42 GB at 8-bit. The 4-bit model fits on a graphics card with 32 GB or more, such as the NVIDIA GeForce RTX 5090 32 GB. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Aion-RP 1.0 (8B) | Aion Labs | 4 Feb 2025 | 33K | $0.80 | $1.60 | Open |
| Voxtral Small | Mistral AI | 15 Jul 2025 | 33K | $0.10 | $0.40 | Open |
| DeepSeek-R1 | DeepSeek | 20 Jan 2025 | 64K | $0.70 | $2.50 | Open |
| DeepSeek V3 0324 | DeepSeek | 24 Mar 2025 | 164K | $0.29 | $1.14 | Open |
| Qwen3-VL 30B-A3B | Alibaba (Qwen) | Apr 2025 | 131K | $0.20 | $0.80 | Open |
| Voxtral Small 24B 2507 | Mistral AI | 15 Jul 2025 | 33K | $0.10 | $0.30 | Open |
Change history
No changes detected since we started tracking this model. We re-check every source daily.