Instructions to use Xylolabs/Hy4-flash-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Xylolabs/Hy4-flash-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Xylolabs/Hy4-flash-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use Xylolabs/Hy4-flash-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Xylolabs/Hy4-flash-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Xylolabs/Hy4-flash-GGUF", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Xylolabs/Hy4-flash-GGUF:Q4_K_M
- Ollama
How to use Xylolabs/Hy4-flash-GGUF with Ollama:
ollama run hf.co/Xylolabs/Hy4-flash-GGUF:Q4_K_M
- Unsloth Desktop
- Pi
How to use Xylolabs/Hy4-flash-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Xylolabs/Hy4-flash-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Xylolabs/Hy4-flash-GGUF with Docker Model Runner:
docker model run hf.co/Xylolabs/Hy4-flash-GGUF:Q4_K_M
- Lemonade
How to use Xylolabs/Hy4-flash-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Xylolabs/Hy4-flash-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Hy4-flash-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Xylolabs/Hy4-flash-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default Xylolabs/Hy4-flash-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Xylolabs/Hy4-flash-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Xylolabs/Hy4-flash-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "Xylolabs/Hy4-flash-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
GGUF quants of tencent/Hy4-flash (220B parameters, 12B active) for llama.cpp, on CUDA, Metal or CPU. The Engram tables sit in a separate file that llama.cpp reads from disk as needed, so only the trunk has to fit in memory.
- Files: quants from Q8_0 down to IQ2_M, the vision tower and the importance matrix.
- Q4_K_M: KL 0.244 from BF16, top-1 85.1 %.
Files
Each quant has two files:
Hy4-flash-<QUANT>-00001-of-00002.ggufis the trunk.Hy4-flash-<QUANT>-00002-of-00002.ggufholds the Engram tables (63.4 GB, FP8 E4M3). It is the same file for every quant (sha256c3589e8789026f7de689a5bd2258daf018deddcbd903a443713051a6d84351a9), and llama.cpp picks it up from the same folder.
Also in this repository: mmproj-Hy4-flash-BF16.gguf (1.04 GB) and mmproj-Hy4-flash-Q8_0.gguf (0.78 GB), the vision tower in BF16 and in Q8_0, and Hy4-flash.imatrix.gguf, the importance matrix.
| Quant | Shard 1 (trunk) | PPL | Mean KL vs BF16 | Same top-1 vs BF16 |
|---|---|---|---|---|
| Q8_0 | 165.50 GB | 29.60 | 0.1741 | 87.9% |
| Q6_K | 129.89 GB | 28.21 | 0.1930 | 87.2% |
| Q5_K_M | 113.37 GB | 29.19 | 0.1868 | 86.9% |
| Q4_K_M | 97.81 GB | 30.96 | 0.2441 | 85.1% |
| Q4_K_S | 92.19 GB | 31.83 | 0.2660 | 84.8% |
| IQ4_XS | 86.94 GB | 29.15 | 0.2745 | 83.8% |
| Q3_K_M | 78.58 GB | 26.99 | 0.3726 | 80.9% |
| IQ3_M | 72.49 GB | 34.95 | 0.4513 | 78.9% |
| IQ3_XXS | 64.89 GB | 31.22 | 0.5094 | 77.2% |
| Q2_K | 61.79 GB | 25.64 | 0.6766 | 73.8% |
| IQ2_M | 56.26 GB | 28.65 | 0.7155 | 72.9% |
How we measured:
- KL and top-1: against the BF16 model (the BF16 trunk with the same Engram file, PPL 30.39), on 24 chunks of 512 tokens of wikitext-2.
Sizes are the trunk only.
Every quant is quantized from the BF16 original, tencent/Hy4-flash. The Engram tables and the vision tower are converted from tencent/Hy4-flash-FP8, whose copies of both are byte-identical to the BF16 original's.
Smaller Engram files
For Q4_K_M and Q3_K_M there are also pairs whose second file holds the Engram tables in Q5_0 or IQ4_NL instead of FP8 E4M3: Hy4-flash-<QUANT>-EQ5_0-0000N-of-00002.gguf and Hy4-flash-<QUANT>-EIQ4_NL-0000N-of-00002.gguf. Their first file is the quant's trunk, byte for byte.
| Pair | Engram file | PPL | Mean KL vs BF16 | Same top-1 vs BF16 |
|---|---|---|---|---|
| Q4_K_M, Engram Q5_0 | 43.56 GB | 31.10 | 0.2542 | 84.4% |
| Q4_K_M, Engram IQ4_NL | 35.64 GB | 31.16 | 0.2584 | 84.6% |
| Q3_K_M, Engram Q5_0 | 43.56 GB | 27.47 | 0.3635 | 80.8% |
| Q3_K_M, Engram IQ4_NL | 35.64 GB | 27.08 | 0.3728 | 81.0% |
Compared with Tencent's Q4_K_M
| Q4_K_M from | Trunk size | PPL | Mean KL vs BF16 | Same top-1 vs BF16 |
|---|---|---|---|---|
| Xylolabs, from BF16 with an F16 LM head (this repository) | 97.81 GB | 30.96 | 0.2441 | 85.05% |
| AngelSlim (Tencent) | 104.99 GB | 31.92 | 0.2814 | 84.44% |
Both were measured against the same BF16 reference, build and text; perplexity on raw text doesn't rank quants of this model reliably, so compare KL and top-1.
Tensor recipe
| Tensor class | Format |
|---|---|
Routed experts ffn_gate_exps, ffn_up_exps, ffn_down_exps (148.6B parameters) |
the quant type of the file |
| Attention (MLA projections, gate, output), shared experts, latent projections, layer-0 dense MLP, token embedding, indexer projections, Engram key/value projections | Q8_0 |
Router ffn_gate_inp, hyper-connection functions, indexer proj and compressor, small Engram weights, norms, biases |
F32 |
LM head output.weight |
F16 (Q8_0 in the Q8_0 file) |
Engram tables per_layer_token_embd (63.4B parameters) |
FP8 E4M3 |
How to run
Hy4-flash support in llama.cpp is pull request #32517 (commit 0a054d0b0) until it is merged. The same build runs on CUDA and on Metal. Tencent's patched build also loads these files.
git clone https://github.com/ggml-org/llama.cpp && cd llama.cpp
git fetch origin pull/32517/head:hy4-flash && git checkout hy4-flash
cmake -B build -DCMAKE_BUILD_TYPE=Release # add -DGGML_CUDA=ON for NVIDIA GPUs
cmake --build build -j --target llama-cli llama-server
./build/bin/llama-cli -m Hy4-flash-Q4_K_M-00001-of-00002.gguf \
--override-tensor '^per_layer_token_embd\.weight$=CPU' --load-mode mmap --lazy-mode on \
-ngl 99 --jinja -c 8192
--override-tensor keeps the Engram tables in host memory, and --load-mode mmap --lazy-mode on reads them from disk only when a prompt needs them. llama-server takes the same flags.
How these were made
- Convert with the PR's
convert_hf_to_gguf.pyplushy4-flash-release-convert.patch(in this repository): the trunk in bf16, the Engram file, and the vision tower with--mmproj. - Build the importance matrix with
llama-imatrixon the Q8_0 trunk, 125 chunks of 512 tokens. - Quantize:
llama-quantize --imatrix Hy4-flash.imatrix.gguf --output-tensor-type f16 --tensor-type-file tensor_types_base.txt <bf16 trunk> <out> <QUANT>. - Split each file into its two parts with
llama-gguf-split.
License and notices
- License: Tencent Hy License, Version 1.0, copied in
LICENSE. Its terms apply to these files, including the extra terms for large Model-as-a-Service operators. - What we changed: we quantized the weights and converted them to GGUF. The conversion patch is
hy4-flash-release-convert.patch. - Notices:
NOTICEnames the source model and its copyright holder. - Xylolabs is not affiliated with or endorsed by Tencent.
Tencent's original model description
The text below is reproduced from the README of tencent/Hy4-flash (the model introduction, highlights, benchmarks, quickstart and deployment sections), copyright Tencent, under the Tencent Hy License (see above). It describes Tencent's original model, not these files, and its usage instructions (Transformers, vLLM, SGLang) are for Tencent's checkpoints; for the GGUF files use "How to run" above. Changes by Xylolabs: heading levels are one level deeper, and image and link paths point to Tencent's repository instead of copies; the wording is unchanged. Tencent's own README is the authoritative version.
Model Introduction
Hy4 flash is our most cost-effective Hy model to date, featuring 220B total parameters (including 64B Engram parameters) with just 12B active parameters per token. It natively accepts text and image inputs, generates text, and supports a context window of up to 1M tokens.
Its 42-layer language backbone consists of one dense feed-forward layer and 41 MoE layers, with identity Hyper-Connections (iHC) supporting inter-layer information flow. A vision encoder (adapted from SigLIP2-So400m-Patch16-Res512) is connected to the backbone through an MLP projector. In addition to the backbone, a built-in 5-layer drafter, DFly2 (0.85B parameters), reuses the target model's KV cache and sparse indices to support long-context speculative decoding at a low, constant cost.
Compared with Hy4, Hy4 Flash introduces three notable architectural changes:
- Hybrid attention. Sparse attention (IndexPool) and sliding-window attention (SWA) are interleaved at a 1:3 ratio.
- LatentMoE. Routed experts operate in a lower-dimensional latent space. Each token activates 16 of 512 routed experts, alongside one shared expert.
- N-gram embedding (Engram). The backbone is augmented with learned bigram and trigram representations, retrieved via multi-head hash lookups.
| Property | Value |
|---|---|
| Overview | |
| Architecture | Mixture-of-Experts (MoE) |
| Total Parameters (excluding Engram, ViT, and DFly2) | 155.5B |
| Engram Parameters | 63.5B |
| ViT Parameters | 0.43B |
| DFly2 Parameters | 0.85B |
| Activated Parameters per Token | Text 11.3B + Vision 0.43B |
| Context Length | 1M (1,048,576 tokens) |
| Language Backbone | |
| Backbone Layers | 42 — 1 dense layer and 41 MoE layers |
| Hidden Size | 3,072 |
| Vocabulary Size | 120,832 |
| Residual Connections | iHC (identity Hyper-Connections) with 4 residual streams |
| Attention — Hybrid Layout | |
| Attention Architecture | Sparse attention + sliding-window attention (SWA) |
| Backbone Layer Pattern | 2 × Sparse → 10 × (3 × SWA → Sparse) |
| Attention Formulation | Multi-head Latent Attention (MLA) |
| Multimodal Position Encoding | Interleaved MRoPE |
| Attention — Layers | Sparse / SWA |
| Backbone Layers | 12 / 30 |
| Attention Heads | 32 / 64 |
| MLA q_lora_rank | 1,024 / 1,024 |
| MLA kv_lora_rank | 512 / 512 |
| QK Head Dimension (non-RoPE + RoPE) | 192 + 64 / 192 + 64 |
| Value Head Dimension | 256 / 256 |
| RoPE Base | 10,000,000 / 10,000 |
| Sparse Context Selection | Up to 2,048 tokens via group-level selection |
| SWA Context Window | 512-token causal window (511 preceding + current) |
| Feed-Forward Networks | |
| Dense FFN Intermediate Size | 13,824 |
| Routed Experts per MoE Layer | 512 |
| Shared Experts per MoE Layer | 1 |
| Activated Routed Experts per Token | 16 |
| MoE Latent Dimension | 1,536 |
| Expert Intermediate Size | 1,536 |
| N-gram Embedding | |
| N-gram Orders | Bigrams and trigrams |
| Backbone Layer Indices (starting from 0) | 1, 11, 21, 31 |
| Hash Heads per N-gram Order | 8 |
| Hash Vocabulary Size per Head | 10.3M |
| Embedding Dimension per N-gram Order | 768 (8 heads × 96 dimensions) |
| Embedding Table Parameters | 63.4B |
| Vision Encoder | |
| Vision Encoder Layers | 27 |
| Vision Encoder Hidden Size | 1,152 |
| Vision Encoder Intermediate Size | 4,304 |
| Vision Encoder Attention Heads | 16 |
| Vision Patch Size | 16 × 16 |
| Vision Position Embedding Size | 128 × 128 |
| Visual Feature Merging | 2 x 2 |
Pretrained model capability
Bits-per-byte (BPB) on internal code & agent validation, lower is better:
Few-shot pretrain benchmark evaluation:
| Category | Benchmark | #Shots | Hy4 flash Base | Hy4 Base | Hy3 preview Base | DeepSeek-V4-flash-Base | DeepSeek-V4-Pro-Base |
|---|---|---|---|---|---|---|---|
| Knowledge | MMLU† | 5 | 88.7 | 91.6 | 87.5 | 89.7 | 91.1 |
| MMLU-Pro† | 5 | 71.1 | 73.9 | 65.8 | 68.6 | 73.4 | |
| MMLU-Redux† | 5 | 87.6 | 90.6 | 87.0 | 88.8 | 90.2 | |
| SuperGPQA† | 5 | 57.8 | 62.7 | 52.3 | 52.5 | 54.8 | |
| C-Eval† | 5 | 92.0 | 95.0 | 90.1 | 91.9 | 93.4 | |
| CMMLU† | 5 | 91.6 | 93.1 | 89.6 | 89.8 | 90.7 | |
| SimpleQA | 5 | 37.5 | 57.2 | 26.4 | 31.3 | 52.1 | |
| Chinese-SimpleQA† | 5 | 74.6 | 83.9 | 69.6 | 71.9 | 76.6 | |
| AGIEval (English)† | 3 | 75.4 | 79.3 | 76.0 | 76.3 | 78.2 | |
| AGIEval (Chinese)† | 3 | 90.6 | 91.2 | 87.8 | 88.5 | 89.8 | |
| Reasoning | HellaSwag (3,000-item subset) | 10 | 85.2 | 87.1 | 85.7 | 85.1 | 86.8 |
| PIQA | 4 | 84.4 | 85.3 | 84.6 | 83.8 | 84.9 | |
| ARC-Challenge | 0 | 95.0 | 97.3 | 96.0 | 97.3 | 97.0 | |
| Social IQa | 0 | 80.1 | 82.7 | 80.5 | 72.5 | 73.1 | |
| KOR-Bench | 3 | 54.7 | 57.6 | 54.6 | 53.4 | 55.4 | |
| C³ | 0 | 77.3 | 82.4 | 75.9 | 74.1 | 78.3 | |
| Math | U-MATH | 5 | 69.8 | 71.6 | 60.9 | 57.4 | 64.8 |
| OCW Courses | 5 | 64.0 | 66.7 | 62.6 | 63.3 | 68.2 | |
| Code | MBPP-plus | 3 | 73.7 | 74.0 | 77.4 | 76.8 | 79.1 |
| Multilingual | Belebele (5-language subset)† | 5 | 93.8 | 95.0 | 94.2 | 94.4 | 95.2 |
| INCLUDE† | 5 | 82.8 | 88.1 | 84.3 | 84.0 | 84.3 | |
| Multimodal | MMMU-Pro (Standard, 10 opts) | 4 | 52.0 | 59.6 | — | — | — |
| SimpleVQA | 4 | 48.5 | 54.5 | — | — | — | |
| CVBench | 4 | 83.4 | 86.7 | — | — | — | |
| RealWorldQA | 4 | 71.1 | 72.3 | — | — | — | |
| TextVQA | 4 | 73.4 | 78.2 | — | — | — | |
| CountBenchQA | 4 | 86.6 | 90.6 | — | — | — |
† Macro-averaged accuracy for the marked text benchmarks. Other text rows use the accuracy metric reported by our evaluation suite. Bold marks the highest available numerical score in each row; it does not indicate statistical significance.
Multimodal results are reported only for Hy4 flash Base and Hy4 Base.
ARC-Challenge and HellaSwag use 299-item and 3,000-item subsets, respectively. INCLUDE uses a 5,000-example Lite subset covering 44 languages. Belebele covers German, Korean, Vietnamese, Spanish, and Russian (4,475 examples in total).
Disclaimer: Because our base model was exposed to a large amount of synthetic instruction data during mid-training, it occasionally fails to follow the expected answer format in few-shot evaluations, which may distort the scores.
Practicality and Cost Efficiency
Optimization Approach
Across training, evaluation, and inference, we aggressively optimized for cost efficiency while preserving intelligence:
- Pre-training: Hy4 flash integrates hybrid attention, LatentMoE, and Engram into its architecture—reducing KV cache size to just 1/24 of Hy3 and 1/6 of Hy4, with extensive scaling ladder experiments ensuring performance meets expectations.
- Post-training: Self-distillation from Hy4 establishes strong general intelligence, while reinforcement learning cuts average end-to-end output tokens by 50%.
- Evaluation: We built WorkIndex, an internal benchmark grounded in typical WorkBuddy tasks, and paired it with human evaluation—focusing on deliverable quality, single-turn output length, and task turnaround time rather than public benchmark scores detached from everyday work.
- Inference: Combining megakernels, 4-bit quantization, and DFly2 pushes decoding speed past 150 tokens/s, enabling low-cost serving at scale.
Task Performance and Cost
Hy4 flash delivers overall task performance slightly above Hy4 preview at a much lower cost per task. On WorkIndex, it scores 42.1, compared with 39.7 for Hy4 preview, while its average cost per task is just 1/13 of Hy4 preview, 1/20 of Hy4, and 1/8 of DeepSeek-V4.1-Flash-1017 (Max tier, peak-hour pricing).
Figure 1: Performance and cost across internal and external tasks. WorkIndex (internal) comprises 8 evaluation sets covering slide creation, slide editing, human-AI slide co-writing, Markdown human-AI co-writing, document editing, spreadsheet repair, audio/video processing, and visual understanding.
Open Benchmarks includes 7 public agent benchmarks: DeepSWE, ProgramBench, Terminal-Bench 4.0, APEX-Agents, AutomationBench, HLE, and OSWorld 2.1.
Figure 2: Average cost per task on WorkIndex. Task scores are 42.1 for Hy4 flash, 39.7 for Hy4 preview, and 51.4 for Hy4.
We recommend Hy4 flash for most everyday productivity tasks, including deep search, document processing, slide creation, simple frontend demos, and computer use. For complex tasks such as long-horizon software engineering, we recommend Hy4 for its higher intelligence ceiling.
User Blind Evaluation
In the blind evaluation, Hy4 flash achieved user satisfaction close to Claude Haiku 5.5, while recording the lowest cost per task and shortest median end-to-end completion time among the evaluated models. Its user satisfaction score was 2.79/4 (Claude Haiku 5.5: 2.81/4), with a median end-to-end completion time of 6.7 minutes and a cost of RMB 0.26 per task.
Figure 3: Blind evaluation with 85 internal WorkBuddy users across 259 tasks spanning 27 categories.
Appendix: Benchmark results
Quickstart
Use Transformers to load the model for local inference, or deploy a server and access it through the OpenAI-compatible API.
Reasoning mode (instruct models):
reasoning_effortsupports"high"(default, thinking enabled) and"no_think"(direct responses). Both examples below use"no_think".Recommended sampling parameters:
temperature=0.9,top_p=1.0.
Transformers
Support for Hy4 flash will be merged into the
transformersmain branch soon. Until then, install from the commit below.
pip install "transformers[torch,vision] @ git+https://github.com/huggingface/transformers.git@refs/pull/50903/head"
The following example generates a brief image description:
from transformers import AutoModelForImageTextToText, AutoProcessor
model_id = "tencent/Hy4-flash"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(model_id, device_map="auto")
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg",
},
{"type": "text", "text": "Describe this image in one sentence."},
],
}
]
inputs = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt",
reasoning_effort="no_think",
).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True))
OpenAI-compatible API
For API access, start a server using the vLLM deployment instructions, then run the following client example:
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
model="hy4-flash",
messages=[
{"role": "user", "content": "Hello! Can you briefly introduce yourself?"},
],
temperature=0.9,
top_p=1.0,
extra_body={"chat_template_kwargs": {"reasoning_effort": "no_think"}},
)
print(response.choices[0].message.content)
Deployment
DFly2 for Speculative Decoding
DFly2 is Hy4 flash's speculative-decoding drafter, trained with AngelSpec and built directly on the target model's Top-k Sparse KV: each draft layer shares the KV cache (KV Share) and the compressed indexer's selection of up to 2,048 positions (Index Share) with its corresponding sparse attention layer. This yields three advantages:
- Constant cost: each draft token attends to at most ~2K keys, regardless of context length.
- Zero extra KV memory: no separate KV cache is maintained for the drafter.
- PD-disaggregation ready: not involved in prefill; the prefill-to-decode transfer adds only one last-layer hidden state.
Quantization
We provide AngelSlim, a more accessible, comprehensive, and efficient toolkit for large model compression. AngelSlim supports a comprehensive suite of compression tools for large-scale multimodal models, including common quantization algorithms, low-bit quantization, and speculative sampling.
For this model, we have provided a GGUF compressed version for end-to-end testing purposes.
Inference Frameworks
For production serving, we recommend using vLLM or SGLang. Please refer to the recipes:
vLLM
Use official prebuilt image vllm/vllm-openai:hy4-flash:
docker run --gpus all \
-p 8000:8000 \
--ipc=host \
-v ~/.cache/huggingface:/root/.cache/huggingface \
vllm/vllm-openai:hy4-flash tencent/Hy4-flash-FP8 \
--tensor-parallel-size 8 \
--speculative-config '{"num_speculative_tokens":5,"method":"dfly"}' \
--attention-backend FLASHMLA_SPARSE \
--tool-call-parser hy_v4 \
--reasoning-parser hy_v4 \
--enable-auto-tool-choice \
--port 8000 \
--served-model-name hy4-flash
SGLang
Use the official prebuilt image lmsysorg/sglang:hy4-flash (multi-arch, x86 and Arm):
docker pull lmsysorg/sglang:hy4-flash
docker run --gpus all \
-p 8000:8000 \
--ipc=host \
lmsysorg/sglang:hy4-flash \
sglang serve \
--trust-remote-code \
--model-path tencent/Hy4-flash-FP8 \
--tp 8 \
--cuda-graph-backend-prefill disabled \
--speculative-algorithm DFLY \
--speculative-dfly-block-size 6 \
--host 127.0.0.1 \
--port 8000
- Downloads last month
- 2,747
Model tree for Xylolabs/Hy4-flash-GGUF
Base model
tencent/Hy4-flash






