← back to catalog · registered 2026-11-16 06:03

guideboardlabs/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Monoglot-GGUF

guideboardlabs Qwen 35B GGUF MoE
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/guideboardlabs%2FQwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Monoglot-GGUF"
Response includes
  • classification m-uncensored
  • files 4
  • benchmarks 11 entries
  • author_summary 3 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
173
Likes
0
Model age
6d ago
created 2026-11-16
Downloads over time
Now 173 → from 0 ↑ 0%
063127190 0 on Nov 16 173 on Nov 22 Nov
Nov 16 → Nov 22 · 7 snapshots · spans 6 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 0 UGI
Natural Intelligence 25.43 UGI
Political lean -19.6% UGI
Sensitive-Info 14.03 UGI
SocPol 2.6 UGI
UGI 16.02 UGI
Willingness (10) 2 UGI
W10-Adherence 0 UGI
W10-Direct 4 UGI
Writing 35.83 UGI

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en
Quantizations
Q4_K
Tags
gguf qwen3.6 moe llama.cpp quantization vocabulary-pruned tokenizer uncensored amd vulkan rdna1 local-llm

Related

Total size
19.4 GB
Files
4
Quantizations
2
Registered
2026-11-16 06:03
Last updated on HF
2026-11-16 14:39

Files by quantization

Q4_K 1 file 19.4 GB
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M-Monoglot-P1G-130K.gguf 19.4 GB b9876abb download
Auxiliary files 3 files 359 KB
monoglot-logo.png 351 KB c6b83b29 download
README.md 6.79 KB 90d6fbd4 download
.gitattributes 1.65 KB b45fdf66 download

README current version from Hugging Face


license: apache-2.0
base_model:

  • Qwen/Qwen3.6-35B-A3B
  • HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive
    language:
  • en
    tags:
  • gguf
  • qwen3.6
  • moe
  • llama.cpp
  • quantization
  • vocabulary-pruned
  • tokenizer
  • uncensored
  • amd
  • vulkan
  • rdna1
  • local-llm

Monoglot

Monoglot 35B-A3B: Qwen3.6-35B-A3B with its vocabulary cut to what English actually uses

One language, on purpose. Third entry in the Monoglot series, after the
27B and the
9B.

This is the entry I expected least and measured the most: only 1.6% of the file came off, and it bought
+26% decode and +62% prompt processing. On a Mixture-of-Experts model that spills most of itself into
system memory, the output head is read in full every single token, so halving the head is not a
file-size trick.

118,300 of 248,320 vocabulary rows removed. Every surviving weight row is bit-identical to the source.

Credit, in order of who did what

Mine is the application to this file, the measurements, and the parts that did not work.

The model, for context

35B total, about 3B active, 256 experts with 8 routed per token, hidden 2048. On a 7.98 GiB card it cannot
fit: it runs with about 7.6 GiB in VRAM and 12.9 GiB spilled to GTT, and it is usable only because each
token activates 8 of 256 experts.

That is the setup that makes this prune pay so much.

vocab rows vocab bytes share of file
Source 248,320 703 MB 3.3%
This file 130,020 368 MB 1.8%
Tensor Type Before After
output.weight Q6_K 417 MB 218 MB
token_embd.weight Q4_K 286 MB 150 MB
File Q4_K_M 21,155,768,832 B 20,825,407,520 B

330 MB smaller, 1.6%. Policy is P1G: ASCII plus math and typography symbols, Greek, box-drawing and
status glyphs, units and currency.

What it bought, measured

llama.cpp 3ba1ce0 Vulkan, RX 5700 XT (8 GB, RDNA1), -ngl 999 -ctk q4_0 -ctv q4_0 -fa on -t 6 --cpu-mask 0x3f, GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM=1, measured at depth 4096. Three reps, card empty
before each run.

llama-bench source this file
pp512 @ 4096 91.95 ± 0.36 149.38 ± 3.02 +62%
tg128 @ 4096 10.16 ± 0.01 12.76 ± 0.01 +26%
GTT in use while running 12.94 GiB 12.09 GiB

Why 1.6% of the file moves the needle: decode here is not a compute problem, it is a transfer problem.
The output head has to be read in full for every generated token no matter how sparse the experts are, and
on this card most of the model sits in GTT over PCIe 3.0 at roughly 13 GB/s. Halving a 417 MB head is
199 MB less per token, which at 13 GB/s is about 15 ms of the ~98 ms each token was taking. Measured gain
was 26%, a little better than that arithmetic, and the prefill gain (62%) is larger still because prefill
was thrashing GTT harder.

So the three entries in this series are three different mechanisms, and none of them was the one the
original post described:

what the prune actually bought
27B crossed back under the VRAM wall: prefill 6.2x, decode 2.4x
9B less per-token bandwidth, no wall to cross: decode +6.1%, prefill flat
35B-A3B halved the one tensor read every token on an already-spilling MoE: decode +26%, prefill +62%

What it costs

Text Source This file Ratio
English prose 30 30 1.00x
Python 41 41 1.00x
Math with ∀ ∑ π ≥ ✓ 27 27 1.00x
French, accented 18 31 1.72x
Japanese 15 40 2.67x
Chinese 15 50 3.33x
Russian 17 93 5.47x

Same table as every other entry, because the policy is the same. If you need multilingual output, use the
source file.

Correctness checks that did pass

  • verify_prune.py --policy P1G: all 731 non-vocabulary tensors byte-identical, gathered rows match their
    source rows, keep-set exactly the policy, every metadata key preserved.
  • Greedy 64-token continuations byte-identical to the source for an English prompt and a code prompt.
  • A tools request on both files returns finish_reason: tool_calls, read_file, and
    {"path":"/etc/hostname"}.

What I did not measure

  • No instruction-following benchmark on this file. Correctness rests on the checks above.
  • No perplexity or KL, because neither is comparable across a vocabulary change.
  • A different build and depth from my own production profile for this model. The numbers above are one
    binary at depth 4096 with the placement fix applied correctly; my production launch of the same family
    uses another build at 32K. The A/B is like-for-like within this table, and the absolute rates are not
    transferable to a different binary.
  • No mmproj, text only.
  • Refusal behaviour not tested.

Using it

llama-server -m Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M-Monoglot-P1G-130K.gguf \
  -c 32768 -ngl 999 -ctk q4_0 -ctv q4_0 -fa on

It wants the same treatment as the source: all layers offloaded, KV quantised, and the placement flag spelled
exactly GGML_VK_DISABLE_HOST_VISIBLE_VIDMEM. A near-miss spelling is accepted by the shell, sets a variable
nothing reads, and silently puts you back in the slow regime.

Files and verification

File Bytes SHA-256
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M-Monoglot-P1G-130K.gguf 20,825,407,520 b9876abbe198501fd08ed5c775e2762590ad4e5047a419aeac2a91ebe41267ae

Licence

Apache-2.0, following the base model. Weights derive from Qwen3.6-35B-A3B and HauhauCS's uncensored tuning.
The pruning tool is linked, not included, because it carries no licence.

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-11-16 Upload README.md with huggingface_hub 61b2d7a 6.8 KB
    Loading...
  2. 2026-11-16 Upload README.md with huggingface_hub d6de2e9 6.7 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration