---

base_model: tencent/Hy3

base_model_relation: quantized

tags:

• gguf
• hy3
• moe
• ds4
• pulsar
• ssd-streaming

---

Hy3 (295B) GGUF for pulsar / ds4 / NeutronStar (SSD streaming, CUDA)

Mixed-precision GGUF of tencent/Hy3

(295B total / 21B active MoE, Apache 2.0) built for SSD-streaming

inference engines: routed experts live on disk and stream per token, so

the model runs on GPUs that cannot hold it.

Runs on pulsar (Rust + CUDA,

recommended) and the NeutronStar

hy3 branch (C, a CUDA port of antirez/ds4).

Measured decode, greedy, warm cache:

| engine | hardware | tok/s |

|---|---|---|

| pulsar | RTX 5060 Ti 16GB + RTX 4060 Ti 16GB, Gen5 NVMe | 7.2 |

| pulsar | RTX 4060 Ti 16GB, Gen4 NVMe | 2.6 |

| NeutronStar/ds4 | RTX 4060 Ti 16GB, Gen4 NVMe | 0.6-1.8 |

Per token only 8 of 192 experts per layer are read (~3GB/token at this

quant); attention, shared experts, and the router stay resident.

Files

| file | provenance | recommendation |

|---|---|---|

| Hy3-ds4-IQ2XXS-AttnQ8-fromBF16.gguf | single quantization straight from the BF16 checkpoint | use this one |

| Hy3-ds4-IQ2XXS-AttnQ8.gguf | requantized from an IQ4 intermediate (see below) | kept for continuity |

Both use the identical recipe and the same importance matrix; they differ

only in what the quantizer saw as input.

fromBF16 (new): tencent/Hy3 BF16 (598GB) converted to a q8_0

intermediate with the AngelSlim

llama.cpp patches (proper hy_v3 architecture support), then quantized

with the imatrix in one step. q8_0 is effectively lossless as an

intermediate, so the routed experts see exactly one lossy quantization.

original: built before the BF16 pipeline existed here, from the IQ4-UD

edition of YanissAmz/Hy3-295B-A21B-GGUF.

The tensors this recipe keeps at Q8_0 passed through essentially lossless,

but the routed experts went through two lossy steps (IQ4_XS/IQ3_S to

IQ2_XXS). At a 2-bit target the 2-bit noise dominates, so the gap is

small, but the fromBF16 file removes it entirely.

Recipe

The layout targets a streaming expert cache: routed experts must be

uniform fixed-size slabs, and everything that makes decisions stays high

precision. Same design as antirez's GLM-5.2 ds4 build, including the MTP

layer riding at Q2_K because importance matrices never cover the draft

layer (imatrix generation runs normal forwards, which skip it).

| Tensors | Type | Why |

|---|---|---|

| routed experts, layers 1-79 (gate/up/down) | IQ2_XXS (imatrix) | streamed from disk per token; uniform slabs |

| routed experts, layer 80 (MTP) | Q2_K | no imatrix coverage exists for the draft layer |

| attention q/k/v/output, all layers | Q8_0 | resident, paid once |

| shared expert + dense layer 0 FFN | Q8_0 | resident |

| nextn.eh_proj (MTP glue) | Q8_0 | tiny, no imatrix coverage |

| token embeddings, output head | Q8_0 | ds4 embed kernel contract |

| router (ffn_gate_inp), expert bias, all norms | F32 | decision makers stay exact |

imatrix: the 125-chunk general-purpose matrix published with the source

repo of the original build, reused for the fromBF16 build.

Usage

pulsar (recommended)

git clone https://github.com/giannisanni/pulsar
cd pulsar
CXX=g++-12 cargo build --release -p engine

./target/release/pulsar-cli -m Hy3-ds4-IQ2XXS-AttnQ8-fromBF16.gguf \
    -p "The capital of France is" -n 64
# or interactive chat:      --chat
# or OpenAI-compatible API: cargo build --release -p serve

Zero-config multi-GPU: pulsar measures each card's PCIe bandwidth at

startup, streams experts over the fastest link, and fills spare GPUs with

resident hot experts. First run is cold; a .warm sidecar makes every

later run start hot. Main knob: PULSAR_CACHE_GB (host expert cache,

defaults to measured free RAM minus a reserve).

NeutronStar / ds4

git clone -b hy3 https://github.com/giannisanni/neutronstar
cd neutronstar && make ds4
./ds4 -m Hy3-ds4-IQ2XXS-AttnQ8-fromBF16.gguf --cuda --ssd-streaming \
  --ssd-streaming-cache-experts 64 --ctx 4096 --nothink

Useful knobs: DS4_CUDA_HOST_EXPERT_CACHE_GB=16 (host expert cache, the

main speed lever) and DS4_CUDA_PARALLEL_FETCH_THREADS=16.

MTP note

blk.80 (the MTP draft layer) is present in both files. pulsar wires it

behind PULSAR_MTP=1 (opt-in): drafts verify correctly at 44 percent

acceptance, but measurements show speculative decoding only pays when the

verify pass is fully cache-resident, which a 30GB-RAM box cannot deliver.

Tencent's own AngelSlim deployment guidance reaches the same conclusion,

enabling MTP only from 2x H20 (192GB) upward. Keep it off for speed; it

is there for bigger boxes.