← back to catalog · registered 2026-11-19 21:04

alesha-pro/Hy4-flash-Uncensored-GGUF

alesha-pro GGUF MoE multimodal
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/alesha-pro%2FHy4-flash-Uncensored-GGUF"
Response includes
  • classification m8
  • files 11
  • author_summary 12 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
58K
Likes
11
Model age
2d ago
created 2026-11-19
Downloads over time
Now 58.4K → from 0 ↑ 0%
021.4K42.8K64.3K 0 on Nov 19 58.4K on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
other
Tags
gguf hunyuan hy4-flash moe uncensored abliterated project-maya rtx3090 vision image-text-to-text base_model:tencent/Hy4-flash base_model:quantized:tencent/Hy4-flash

Related

Total size
187 GB
Files
11
Quantizations
2
Registered
2026-11-19 21:04
Last updated on HF
2026-11-19 21:08

Files by quantization

BF16 1 file 996 MB
mmproj-Hy4-flash-bf16.gguf 996 MB a1504cb1 download
Auxiliary files 10 files 187 GB
Hy4-flash-Q3_K-00001-of-00002.gguf 80.3 GB 22d41729 download
Hy4-flash-Q3_K-00002-of-00002.gguf 59.0 GB ecd6a0ec download
Hy4-flash-IQ2-00001-of-00002.gguf 47.6 GB 24f0a623 download
Hy4-flash-refusal-directions.bin 4.03 MB a6f50aff download
routing-profile.txt 793 KB 3b450022 download
routing-profile-1gpu.txt 249 KB d900196c download
LICENSE 13.6 KB 2be6f885 download
README.md 4.76 KB 0ce73c18 download
.gitattributes 1.75 KB 00a663c7 download
SHA256SUMS 395 B 2be540f5 download

README current version from Hugging Face


base_model: tencent/Hy4-flash
base_model_relation: quantized
pipeline_tag: image-text-to-text
library_name: gguf
license: other
license_name: tencent-hy-license
license_link: LICENSE
tags:

  • gguf
  • hunyuan
  • hy4-flash
  • moe
  • uncensored
  • abliterated
  • project-maya
  • rtx3090
  • vision

Hy4-flash Uncensored GGUF for 4, 2 or 1 RTX 3090

Tencent's 220B Hy4-flash with the full 262144 token context, image input and MTP, on consumer cards, with a refusal vector that removes most refusals. Runs on my Project Maya branch: alesha-pro/project-maya, branch hy4-flash (docs). Stock llama.cpp does not load it.

Setup Decode, tok/s Prefill, tok/s RAM
4x RTX 3090, Q3_K 176 to 251 2947 about 60 GiB
2x RTX 3090, Q3_K 70 to 104 1225 137 GiB
2x RTX 3090, IQ2 95 to 123 1999
1x RTX 3090, Q3_K 37 to 54 1510 137 GiB, 78 GiB with Engram on NVMe
1x RTX 3090, IQ2, Engram on NVMe 54 to 68 1184 to 1199 45 GiB

Files

File GB What
Hy4-flash-Q3_K-00001-of-00002.gguf 86.2 trunk: experts Q3_K/Q4_K, attention Q8_0, MTP layer Q3_K/Q8_0
Hy4-flash-IQ2-00001-of-00002.gguf 51.1 the same trunk with IQ2 experts: faster, further from the base
Hy4-flash-Q3_K-00002-of-00002.gguf 63.4 Engram table, used with either trunk
mmproj-Hy4-flash-bf16.gguf 1.04 vision
Hy4-flash-refusal-directions.bin 0.004 the uncensored vector (HY4F_ABLATE)
configs/, tokenizer/, routing-profile*.txt, tools/ server configs, tokenizer, expert heat, the scripts behind every file

Get one trunk and the Engram table: 150 GB (Q3_K) or 115 GB (IQ2).

Uncensored

The weights are stock. The vector holds refusal directions for every layer and each of the four hyper-connection streams, and the engine projects them out of the residual stream as it runs. The configs here have it on (HY4F_ABLATE); delete that line for the stock model.

Held-out refusals, judged by the stock model Stock Uncensored
AdvBench 64 + JailbreakBench 82, thinking off 139 32
AdvBench 24, thinking on 22 3
Harmless requests 64 1 0

Cost: on long text the top token matches the stock model in 85.7% of positions (two stock runs agree on 88.3%), median KL 0.014. Most refusals are gone, not all.

Quality of the quants

Against the 4 card Q3_K run on 512 positions: 2 cards 88.3% same top token, 1 card 88.5% (both inside the noise of the test), IQ2 experts 74 to 76%. AngelSlim report their Q3_K within 0.5 points of BF16 on their suites. No task benchmarks of my own.

Run

git clone -b hy4-flash https://github.com/alesha-pro/project-maya && cd project-maya
cmake -S . -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DSTRATA_ENABLE_CUDA=ON \
  -DCMAKE_CUDA_ARCHITECTURES=86 -DSTRATA_BUILD_TESTS=OFF
cmake --build build -j 24 --target maya-hy4f
# edit the paths in the config, then
python -m serve.server --engine maya --config configs/hy4f-2gpu.json --host 127.0.0.1 --port 18000

OpenAI chat API on /v1. For the IQ2 trunk replace the first --gguf path. For the NVMe mode (1 card) put the Engram file on NVMe and keep HY4F_ENGRAM_IO=direct, as in hy4f-1gpu-iq2-nvme.json.

What I changed (Tencent Hy License, section 4)

  • Hy4-flash-Q3_K-00001-of-00002.gguf: AngelSlim's file with the MTP layer (blk.42, 21 tensors) requantized from BF16 to Q3_K/Q8_0/F32 so it fits next to 256K context on 24 GB cards (tools/requant_mtp_q3k.py). Everything else as it was.
  • Hy4-flash-IQ2-00001-of-00002.gguf: the file above with the 123 routed expert tensors of layers 1 to 41 copied byte for byte from AtomicChat's IQ2 file (rev dc1525fe); nothing requantized (tools/merge_experts_gguf.py).
  • Hy4-flash-Q3_K-00002-of-00002.gguf: AngelSlim's Engram file, byte for byte.
  • mmproj-Hy4-flash-bf16.gguf: Tencent's vision tower in BF16, converted with AngelSlim's llama.cpp patch.
  • Hy4-flash-refusal-directions.bin, routing-profile*.txt: mine, measured on this model (tools/abliteration/).

Credits

Model: Tencent. Q3_K quantization: AngelSlim. IQ2 experts: AtomicChat. Engine family: Project Maya by mw00 and Peasant Smith, grown out of Strata by Niko1221. GGUF formats and kernels: llama.cpp and ggml.

License

Tencent Hy License, Version 1.0, derived from Apache 2.0 with extra terms for large Model-as-a-Service businesses in section 10.

README history 4 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-19 IQ2 trunk as the complete set Hy4-flash-IQ2_XXS-0000{1,2}-of-00002 (no new da... 239e9f9 4.9 KB
    Loading...
  2. 2026-11-19 Uncensored: refusal vector (HY4F_ABLATE) on in all configs, abliteration scri... b7f822d 4.8 KB
    Loading...
  3. 2026-11-19 IQ2 trunk file, fast 1 GPU and NVMe Engram configs, 1 GPU routing profile, up... d0a9a25 11.2 KB
    Loading...
  4. 2026-11-19 Hy4-flash Q3_K with a quantized MTP layer, vision projector, tokenizer, routi... c1f6716 6.6 KB
    Loading...

Discussions 1 thread

  1. 2026-11-21 Help whats wrong open 2 💬 #1
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration