Run LLMs locally with a single file
Download the file and run it. Delete the file when you are done.
No environment setup. No library installation. No annoying clean up.
Compare uncensored variants β
How to use
These bundled files are too large to run on Windows. Use a separate llamafile binary with the source GGUF files, as shown in the llamafile docs.
Download the llamafile (e.g. Q4_K_M).
Open a terminal on Linux or macOS.
Grant execute permission.
chmod +x Huihui-Qwen3.8-27B-abliterated-Q4_K_M.llamafileRun the file.
bash Huihui-Qwen3.8-27B-abliterated-Q4_K_M.llamafile # Or run directly if your system supports it. ./Huihui-Qwen3.8-27B-abliterated-Q4_K_M.llamafile- CLI: Chat directly in the current terminal.
- Web UI: Open localhost:8080 in your browser.
- API: Connect an OpenAI-compatible client to
http://127.0.0.1:8080/v1.- The chat endpoint is
/v1/chat/completions. - The server supports 4 parallel requests by default.
- The chat endpoint is
Press Control-C to stop the process.
For more details, run with
--helpor read the llamafile docs.bash Huihui-Qwen3.8-27B-abliterated-Q4_K_M.llamafile --help
ubuntu@ubuntu > ./Huihui-Qwen3.8-27B-abliterated-Q4_K_M.llamafile
βββ βββ ββββββ ββββ ββββ ββββββ ββββββββββββββ ββββββββ
βββ βββ βββββββββββββ βββββββββββββββββββββββββββ ββββββββ
βββ βββ βββββββββββββββββββββββββββββββββ ββββββ ββββββ
βββ βββ βββββββββββββββββββββββββββββββββ ββββββ ββββββ
βββββββββββββββββββ ββββββ βββ ββββββ ββββββ βββββββββββββββββββ
βββββββββββββββββββ ββββββ ββββββ ββββββ βββββββββββββββββββ
software: llamafile 0.10.5
model: Huihui-Qwen3.8-27B-abliterated-Q4_K.gguf
compute: Apple Metal GPU
server: http://127.0.0.1:8080
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
>>>
Collection and comparison
Part of Qwen3.8-27B Uncensored Variant Llamafiles.
Chart source code#@title Performance versus uncensored response rate
import matplotlib.pyplot as plt
from statistics import mean
# Source: [Abliterlitics](https://web.archive.org/web/20260909182157/https://abliterlitics.dev/models/qwen38-27b/)
# Archived FP8 results, not measurements of these GGUFs.
# Columns: MMLU-Pro, GPQA, BBH, MuSR, IFEval, HellaSwag, ARC-C, WinoGrande,
# PIQA, GSM8K, TQA-MC1, TQA-MC2, TQA-Gen, HumanEval, HarmBench judge ASR (%).
data = {
"Official": [62.82, 28.28, 75.16, 45.90, 82.07, 74.79, 59.90, 71.11, 79.65, 91.21, 44.43, 66.98, 55.08, 79.3, 4.5],
"Heretic ARA": [62.65, 27.27, 74.78, 45.90, 82.26, 74.19, 60.24, 71.27, 79.65, 91.51, 44.19, 65.74, 55.08, 82.3, 57.5],
"Apostate": [62.81, 29.80, 74.22, 45.63, 82.99, 74.54, 60.84, 71.19, 79.87, 91.81, 44.19, 65.02, 53.37, 79.9, 78.7],
"coder3101": [62.66, 28.79, 74.78, 46.16, 83.36, 74.53, 59.90, 70.09, 79.60, 91.21, 43.57, 64.63, 53.12, 80.5, 70.0],
"OrcaRouter": [62.78, 27.27, 74.29, 45.37, 82.44, 74.16, 59.90, 71.27, 79.65, 90.75, 44.55, 65.48, 53.49, 78.7, 82.2],
"Ultra Heretic": [62.25, 26.77, 74.92, 45.24, 82.26, 74.34, 58.28, 71.11, 79.22, 90.75, 39.90, 60.54, 48.84, 79.3, 70.5],
"Huihui": [62.67, 32.32, 74.69, 45.63, 81.89, 74.10, 60.07, 71.35, 79.43, 91.74, 41.86, 63.71, 52.02, 78.7, 75.6],
"OBLITERATUS": [56.49, 30.30, 70.44, 45.90, 77.63, 73.90, 62.03, 69.93, 80.69, 92.19, 38.19, 55.82, 45.04, 45.7, 63.9],
"Blackfrost": [60.89, 25.76, 73.36, 42.72, 82.44, 73.31, 58.19, 68.11, 79.82, 89.76, 43.45, 64.08, 51.04, 70.7, 68.5],
}
# Not in this collection; remove these filters to include all source rows.
del data["Apostate"]
del data["coder3101"]
# Equal mean of 12 families; average TQA's three scores first. Exclude perplexity.
performance = [mean(row[:10] + [mean(row[10:13]), row[13]]) for row in data.values()]
# Blog judge ASR excludes degenerate responses; it is not final-answer usability.
uncensored = [row[-1] for row in data.values()]
fig, ax = plt.subplots(figsize=(9, 6), layout="constrained")
ax.scatter(performance, uncensored, s=55)
for name, x, y in zip(data, performance, uncensored):
ax.annotate(name, (x, y), xytext=(6, 6), textcoords="offset points")
ax.set(xlabel="Performance β mean of 12 benchmark families (%)",
ylabel="Uncensored response rate β HarmBench judge ASR (%)",
title="Qwen3.8-27B variants", ylim=(0, 100))
ax.margins(x=0.20)
ax.grid(alpha=0.2)
fig.savefig("qwen38-performance-vs-asr.png", dpi=180, bbox_inches="tight")
plt.show()
Other variants:
- Qwen3.8 27B
- Heretic ARA Uncensored (Best Performance)
- OrcaRouter Uncensored (Best Uncensored)
- Ultra Heretic Uncensored
- Huihui Uncensored (This one)
- OBLITERATUS Uncensored
- Blackfrost Uncensored
The suggestions are based on imperfect benchmarks and should not be trusted blindly. Try the variants yourself with your own use case.
All data came from the Abliterlitics review (snapshot), which also contains more detailed analysis of more uncensored model variants. I am not the author, nor did I replicate the experiments myself.
Settings for Huihui Uncensored GGUF Llamafiles
- Model creator: huihui-ai
- Original model: Qwen/Qwen3.8-27B
- Quantized GGUF files used: huihui-ai/Huihui-Qwen3.8-27B-abliterated-GGUF
- Commit hash
8f1b52408a2f6e317535190c9386f776cacf0079 - Commit message: Add files using upload-large-folder tool
- Commit hash
- Llamafile version: 0.10.5, mozilla-ai/llamafile
- Commit hash
486e6c5f9356eae50b851b07517bfae1f2420193 - Commit message: docs(support): document the Vulkan GPU backend (#1029) (#1033)
- Commit hash
- Quantizations: Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0.
- Validation: Linux text generation; details in
validation/. - Vision: text GGUF; upstream projector files remain separate.
- MTP: source tensors retained; validation uses standard decoding.
.argscontents:
-m
Huihui-Qwen3.8-27B-abliterated-Q4_K.gguf
...