Downloads · 30 days
43
13% of all-time downloads
neopolita/Qwen3.6-35B-A3B-Saikei-8bit-gguf
Qwen3.6-35B-A3B-Saikei-8bit-gguf is a text generation model from neopolita. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Downloads · 30 days
43
13% of all-time downloads
All-time downloads
336
Public
Repo size
36.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf36.9 GB · 100%
From the Hugging Face model README

Q8_0 GGUF of Qwen3.6-35B-A3B-Saikei — the intact 35B MoE improved by a short knowledge-distillation pass from Qwen3.8-2.4T-A95B. Nothing pruned, nothing removed; runs anywhere llama.cpp runs.
Saikei (栽景) are Japan's planted landscapes — miniature living scenes grown whole on a tray, where nothing is cut away: the art is in the cultivation. Where our Niwaki releases prune the tree, this model prunes nothing. It is the reference model, refined in place.
A paper with the full method and measurements is coming soon.
The unmodified 35B/3B-active MoE distilled (a 3M-token plan stopped at ~2.1M tokens at a probe plateau; released checkpoint step 1769, ~1.8M tokens) against top-20 teacher logprobs from the 2.4T teacher (tokenizer-identical); trainables (per-layer output maps + shared experts) folded back, then exported bf16 → quantized Q8_0 with llama.cpp. See the mlx release for the paired MLX-protocol benchmarks (wt2/c4/tasks/gsm8k vs reference).
Measured on this exact Q8_0 file (llama-perplexity, full-file
WikiText-2 test; C4 slice, 512 chunks):
| file | wiki ppl ↓ | c4 ppl ↓ |
|---|---|---|
| Qwen3.6-35B-A3B-Saikei-Q8_0.gguf (34 GB) | 6.59 | 11.64 |
Note llama-perplexity numbers are not directly comparable to the MLX protocol on the mlx card — different windows and tokenizer handling; within-file comparisons are exact.
llama-cli -m Qwen3.6-35B-A3B-Saikei-Q8_0.gguf -cnv \
-p "Explain speculative decoding in two paragraphs."
Distillation heal of mlx-community/Qwen3.6-35B-A3B-8bit (teacher
Qwen/Qwen3.8-2.4T-A95B), folded, exported via convert_hf_to_gguf.py
(bf16, --no-mtp), quantized Q8_0 (llama.cpp).