中文Sign up

pipenetwork/GLM-5.3-Flash-REAP25-MLX-mixed-4_8bit

🤗 Hugging Face sourceimage-text-to-textmit238B params476 GBsafetensors✓ 15 checksumsupdated today
Submit in one command

Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo pipenetwork/GLM-5.3-Flash-REAP25-MLX-mixed-4_8bit ./model-folder
Needs a seeder →

GLM-5.3-Flash-REAP25-MLX-mixed-4_8bit

MLX (Apple Silicon) build of GLM-5.3-Flash — 320B-A18B hybrid of 34 Kimi-Delta linear-attention layers and 11 DeepSeek-sparse-attention (NoPE MLA + lightning indexer) layers with manifold-constrained hyper-connections — quantized to 4-bit experts / 8-bit everything else.

These files are modified: converted from the upstream bfloat16 release (GLM-5.3-Flash-BF16) to MLX and quantized; the architecture is unchanged. The multi-token-prediction layer (layer 45) is not included. The vision tower is carried in bfloat16.

Runtime

glm5_next landed in mlx-vlm main on 2026-08-26 (no release carries it yet). Validating that port against transformers 5.16 at tiny scale found two numerical bugs and two epsilon mismatches, which the runtime in https://github.com/PipeNetwork/glm53-flash-mlx fixes; parity is 1e-6 end to end, exact on cached decode.

what reference mlx-vlm main effect
swiglu_limit gate clamped at 10, up at ±10, in every text MLP no clamp anywhere in the text stack formula mismatch on all 45 FFN blocks
mHC base/scale dtype float32 converter casts to bf16; the Metal kernel then reads base as float4 comb mixing matrix off by ~0.5 on every layer of a converted checkpoint
MLA low-rank norm eps rms_norm_eps = 1e-5 1e-6 small
indexer LayerNorm eps 1e-6 1e-5 small

This checkpoint keeps the mHC arrays and KDA decay parameters in float32 as stored, so it is safe in either runtime; the clamp is a compute-path fix and needs the patched runtime:

git clone https://github.com/PipeNetwork/glm53-flash-mlx && cd glm53-flash-mlx && pip install -r requirements.txt
python scripts/smoke_generate.py /path/to/GLM-5.3-Flash-REAP25-MLX-mixed-4_8bit

from glm53_flash_mlx.load import load
model, processor = load("/path/to/GLM-5.3-Flash-REAP25-MLX-mixed-4_8bit")

REAP pruning

This build keeps 216 of 288 routed experts per MoE layer (25% pruned; the 3 dense layers, attention, shared experts, router and vision tower are untouched), chosen by REAP saliency — mean router_weight × ‖expert_output‖ over 65,536 calibration tokens (wikitext-2 train, ten languages of Wikipedia and code; zero 32-gram overlap with the eval set), collected by running the full 8-bit build. Kept experts carry 86.9% of saliency mass on average; two disjoint halves of the calibration set pick the same kept set 93.3% of the time. The pruning was applied to the already-quantized build (equivalent to pruning bf16 and requantizing). Saliency retention is not a quality measure — the perplexity below is.

Size and what is quantized

139.1 GB on disk (bfloat16 upstream: 642.7 GB).

group share of parameters this build
routed experts (switch_mlp, 42 layers × 288) 304B (97%) 4-bit, group 64
KDA and MLA projections, shared experts, dense MLPs, embeddings, lm_head ~9B 8-bit, group 64
lightning-indexer projections 0.06B 8-bit, group 64
MoE router + correction bias, mHC arrays (fp32), KDA A_log/dt_bias (fp32), convolutions, norms — as stored
vision tower 0.56B bfloat16

Quality

Perplexity on wikitext-2 (test), 288,627 tokens in 141 windows of 2048, every build scored on identical windows through this runtime. The 643 GB bfloat16 model does not fit a 512 GB machine, so the 8-bit build is the anchor (on every model we have measured, 8-bit has been statistically indistinguishable from bfloat16). Per-window NLL differences against 8-bit, bootstrapped over one shared index set (20,000 resamples):

build size perplexity ΔNLL/token vs 8-bit [95% CI] windows worse
8bit 334.1 GB 3.4607 — —
6bit 255.9 GB 3.4646 +0.0011 [−0.0017, +0.0038] 89/141
mixed-4_8bit 181.9 GB 3.5705 +0.0312 [+0.0271, +0.0355] 131/141
4bit 177.6 GB 3.7549 +0.0816 [+0.0755, +0.0879] 140/141
REAP25-mixed-4_8bit 139.1 GB 4.2249 +0.1995 [+0.1657, +0.2377] 139/141
REAP37-mixed-4_8bit 118.3 GB 4.8752 +0.3427 [+0.2968, +0.3929] 141/141
REAP50-mixed-4_8bit 96.3 GB 6.0757 +0.5628 [+0.5071, +0.6219] 141/141
REAP25-4bit — 4.4361 +0.2483 [+0.2135, +0.2873] 141/141
REAP37-4bit — 5.1057 +0.3889 [+0.3424, +0.4393] 141/141
REAP50-4bit — 6.3840 +0.6123 [+0.5552, +0.6722] 141/141

Read the interval, not the point estimate; "windows worse" counts how many of the 141 windows the build lost outright.

Against the 8-bit anchor: 6-bit +0.1%, mixed 4/8-bit +3.2%, uniform 4-bit +8.5%. Routed experts are 97% of the parameters; the mixed build keeps the other ~9B (KDA and MLA projections, shared experts, dense layers, embeddings) at 8-bit for 4.4 GB more than uniform 4-bit.

Greedy generation (a collapse detector, not a ranking) is coherent on every published build.

License

MIT, as the upstream model. Port code: https://github.com/PipeNetwork/glm53-flash-mlx.