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 (revdc1525fe); 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.