Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF
Underdog Saluki 27B 1.0 + MTP with refusals removed. It answers requests that the original model refuses, and otherwise behaves close to the original: same file size, same speed, MTP self-speculative decoding still works.
Params
27.0 B
Context
—
Downloads 30d
325 K
Likes
61
Download history
daily snapshots · 10 days325 K141 K
Nov 1Nov 4Nov 7Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| Underdog-Saluki-27B-1.0-IQ2-mix-MTP-abliterated.gguf | Q2 | 8.3 GB | 13.7 GB | ✅ Runs comfortably |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ ollama run underdog-saluki-27b-1-0-mtp-abliterated-gguf # pin the quantization explicitly $ ollama run underdog-saluki-27b-1-0-mtp-abliterated-gguf-q2
$ huggingface-cli download Kujira/Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF-GGUF \
Underdog-Saluki-27B-1.0-IQ2-mix-MTP-abliterated.gguf --local-dir .
$ llama-cli -m Underdog-Saluki-27B-1.0-IQ2-mix-MTP-abliterated.gguf \
-c 8192 -ngl 99 -t 8 --color
$ curl -s https://aimodelscomparison.com/api/v1/models/underdog-saluki-27b-1-0-mtp-abliterated-gguf
{
"hf_id": "Kujira/Underdog-Saluki-27B-1.0-MTP-Abliterated-GGUF",
"params_b": 27.00,
"context_length": null,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 325062,
"vram_estimates": [
{ "quant": "Q2", "gb": 13.7 }
],
"updated_at": "2026-11-01T01:00:23Z"
}
Specifications
- Parameters
- 27.0 B
- Licence
- apache-2.0
- First seen on the Hub
- 2026-10-09
- Training datasets
- undisclosed
- Added to our catalog
- 2026-11-01
Compare with any text-generation model
Popular comparisons
Appears in