Downloads · 30 days
128
22% of all-time downloads
darkmaniac7/Qwen3.5-35B-A3B-heretic-v2-GGUF
Qwen3.5-35B-A3B-heretic-v2-GGUF is a text generation model from darkmaniac7. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
llmfan46's Heretic abliteration of the Qwen3.5 35B-A3B mixture-of-experts model as one Q2K imatrix GGUF file (mradermacher's quant, renamed) for high-memory phones in TokForge.
Downloads · 30 days
128
22% of all-time downloads
All-time downloads
590
Public
Repo size
13.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf13.2 GB · 100%
From the Hugging Face model README
llmfan46's Heretic abliteration of the Qwen3.5 35B-A3B mixture-of-experts model as one Q2_K imatrix GGUF file (mradermacher's quant, renamed) for high-memory phones in TokForge.
Published by TokForge for on-device inference.
| What it is | Chat model (MoE, 35B total, about 3B active) |
| Format | GGUF, Q2_K with imatrix, one file |
| Runs on | Android phones (llama.cpp) |
| Phone class | 16 GB RAM or more (TokForge catalog; opt-in on every phone) |
| Download | 13.2 GB (1 file) |
| Base model | llmfan46/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved |
| License | Apache-2.0 |
Runs on-device in the TokForge app.
Collections: TokForge GGUF Models.
| File | Size | What it is |
|---|---|---|
Qwen3.5-35B-A3B-heretic-v2-Q2_K.gguf | 13.2 GB | The model (Q2_K imatrix GGUF; same bytes as mradermacher's i1-Q2_K file, renamed) |
Weighted/imatrix Q2_K GGUF of the heretic v2 abliterated Qwen3.5-35B-A3B MoE, republished under a shorter neutral file name for the TokForge model catalog.
All credit for the model, the abliteration pass, and the quantization goes to the upstream authors listed below. This repo mirrors a single upstream file, renamed only; the bytes are identical.
qwen35moe in llama.cpp terms).| file | bytes | sha256 |
|---|---|---|
Qwen3.5-35B-A3B-heretic-v2-Q2_K.gguf | 13,246,130,880 | cb60a6e0acbb93c9ab5e85aade11d9ab1fb81ea7e63dcf80123f4656b079a49f |
The file is byte-identical to the upstream file Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved.i1-Q2_K.gguf in mradermacher/Qwen3.5-35B-A3B-uncensored-heretic-v2-Native-MTP-Preserved-i1-GGUF, renamed only.