Underdog Saluki 27B 1.0 MTP Abliterated needs about 11.0 GB of memory at its main file (a 8.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
Underdog Saluki 27B 1.0 MTP Abliterated – a 27B Qwen3.8‑based model with tool‑calling and MTP support
Underdog Saluki 27B 1.0 MTP Abliterated is a 27‑billion‑parameter Qwen3.8‑derived model. It runs in stock llama.cpp and supports MTP drafting. The model is released under Apache‑2.0 and includes tool‑calling capabilities.
Good at
- Tool calling with MTP drafting
- Chat and agent tasks
- Reasoning with thinking mode
Limits
- Requires 8.35 GB GGUF file, 11 GB VRAM at 8 k context
- No vision support in base file
- License is Apache‑2.0
Best for
- Local LLM deployment with tool usage
- MTP‑based drafting workflows
- Chat‑based agent applications
Who it’s for. Developers and researchers who need a local LLM with robust tool‑calling and MTP drafting. The model is suitable for on‑premise inference on GPUs with at least 12 GB VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 8.3 GB | 11.0 GB | Too big | Get file → |
The only available quant is the default 8.35 GB file. It requires about 11 GB VRAM at 8 k context. For 12 GB cards, 40 k context fits; 64 k context may spill VRAM. No other quants are listed.
What GPU do you need for Underdog Saluki 27B 1.0 MTP Abliterated?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is the main file (8.3 GB file, about 11.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Underdog Saluki 27B 1.0 MTP Abliterated
How much VRAM does Underdog Saluki 27B 1.0 MTP Abliterated need?
About 11.0 GB at its main file with an 8K context window. That is the 8.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Underdog Saluki 27B 1.0 MTP Abliterated on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Underdog Saluki 27B 1.0 MTP Abliterated GGUF?
It depends on the quant: file is 8.3 GB.
What context length does Underdog Saluki 27B 1.0 MTP Abliterated support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.
Where can I download Underdog Saluki 27B 1.0 MTP Abliterated GGUF?
The files are on Hugging Face in the Kujira/Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Underdog Saluki 27B 1.0 MTP Abliterated use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Does the model support vision?
The base GGUF file is text only. Vision requires a separate 0.6‑0.9 GB add‑on.
What license applies to this model?
The model is released under the Apache‑2.0 license.