Model Intelligence Sheet
jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF overview
ATX Swift Qwen3.8 27B Uncensored PTQ1 0 MTP GGUF Ternary 1.75 bit quantization PTQ1 0 with native Multi Token Prediction MTP draft head for d0xin/Swift Qwen3.8…
Runs locally from ~6.70 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP.gguf | GGUF | GGUF | 6.70 GB | Download |
Model Details
| Model ID | jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF |
|---|---|
| Author | jakeatx |
| Pipeline | text-generation |
| License | other |
| Base model | d0xin/Swift-Qwen3.8-27B-Uncensored-BF16 |
| Last modified | 2026-09-18T17:29:58.000Z |
Model README
---
license: other
license_name: swift-open-license-1.0
library_name: gguf
pipeline_tag: text-generation
base_model: d0xin/Swift-Qwen3.8-27B-Uncensored-BF16
tags:
- gguf
- llama.cpp
- qwen3_8
- ternary
- ptq1_0
- uncensored
- mtp
---
ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF
Ternary 1.75-bit quantization (PTQ1_0) with native Multi-Token Prediction (MTP) draft head for d0xin/Swift-Qwen3.8-27B-Uncensored-BF16.
Overview
- Quant Format:
PTQ1_0(1.75 bpw ternary, 5 trits packed per byte, ~2.10 BPW container with critical tensors preserved). - MTP Speculative Decoding: Native layer 64 (
blk.64.*) fused directly into the model (qwen35.block_count: 65). Ready for self-speculative decoding inllama.cppandllamAmperewithout needing an external drafter model. - Size: 7,199,369,088 bytes (6.70 GiB)
- SHA256:
c7c47656be2f50a6a37d50e36d0bf5fa47d9d563243e6dc2ae2acaa0363218f9
Usage with llama.cpp / llamAmpere
llama-server -m ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP.gguf -ngl 99 -fa on -c 32768 --spec-type draft-mtp --spec-draft-n-max 3 --spec-draft-p-min 0.45Run jakeatx/ATX-Swift-Qwen3.8-27B-Uncensored-PTQ1_0-MTP-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models