← back to catalog · registered 2026-10-03 09:58

ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF

ImposterOnline 8B GGUF second-order
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/ImposterOnline%2FPyrex-8B-Instruct-Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 7
  • author_summary 6 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
64
↑ 367% in 90 days
Likes
0
Model age
7w ago
created 2026-10-02
Downloads over time
Now 682 → from 146 ↑ 367%
119325530736 146 on Oct 3 682 on Nov 22 682 on Nov 21 OctNov
Oct 3 → Nov 22 · 51 snapshots · spans 50 days

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.

Variants by this author 2 formats · 812 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Quantizations
F16
Tags
gguf license:mit endpoints_compatible region:us conversational

Related

Total size
31.2 GB
Files
7
Quantizations
2
Registered
2026-10-03 09:58
Last updated on HF
2026-10-10 11:52

Files by quantization

F16 1 file 14.2 GB
pyrex-f16.gguf 14.2 GB d0db3dd8 download
Auxiliary files 6 files 17.0 GB
pyrex-q8_0.gguf 7.54 GB 2a3657ad download
pyrex-q5_k_m.gguf 5.07 GB 94b58f2c download
pyrex-q4_k_m.gguf 4.36 GB 8c351f3c download
.gitattributes 1.90 KB fedcee34 download
README.md 916 B a62983a7 download
Modelfile 623 B f354a671 download

README current version from Hugging Face


license: apache-2.0
base_model: ImposterOnline/Pyrex-8B-Instruct-Uncensored
tags: [code, coding, uncensored, gguf, qwen2.5]

Pyrex 8B Instruct Uncensored — GGUF

Quantized GGUF builds of Pyrex 8B Instruct Uncensored, our uncensored coding model. Chat format: chatml.

File Size Notes
pyrex-q4_k_m.gguf 4.4 GB Recommended
pyrex-q5_k_m.gguf 5.1 GB Higher quality
pyrex-q8_0.gguf 8.1 GB Near-lossless
pyrex-f16.gguf 15.2 GB Full precision

Ollama

ollama create pyrex-8b -f Modelfile
ollama run pyrex-8b "write a python function that merges overlapping intervals"

llama.cpp

./llama-cli -m pyrex-q4_k_m.gguf -p "<|im_start|>user\nYour question\n<|im_end|>\n<|im_start|>assistant\n" -n 512 -c 8192

Apache-2.0.

README history 9 versions

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

  1. 2026-10-10 docs: rebrand GGUF as original Pyrex architecture d9760d6 972 B
    Loading...
  2. 2026-10-10 docs: add verified benchmarks (HumanEval 87.2%, MBPP 6.23%, SWE 100%) 5d459bd 949 B
    Loading...
  3. 2026-10-10 docs: set GGUF model name to Pyrex-8B-Instruct-Uncensored 8b235c0 521 B
    Loading...
  4. 2026-10-10 docs: finalize Pywitz GGUF card 56419ee 760 B
    Loading...
  5. 2026-10-10 docs: Pyritz GGUF card 8d31fe7 465 B
    Loading...
  6. 2026-10-03 pyrex filenames in README 41fed78 887 B
    Loading...
  7. 2026-10-03 rename to Pyrex 04d274c 1004 B
    Loading...
  8. 2026-10-02 README with license metadata cf1f79e 991 B
    Loading...
  9. 2026-10-02 GGUF usage README 660b6cc 854 B
    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