SAVRN
Search Contact SAVRN

Open-weight model

DiStil-Qwen3-1.7B-uncensored

by Convergent Intelligence reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored

Uncensored Distillation of Qwen3-1.7B — Alignment-Free Capability Transfer DiStil-Qwen3-1.7B-uncensored is a 1.7B parameter model produced by distilling Qwen3 with uncensored SFT data, removing alignment-imposed refusal behaviors while preserving the base…

Parameters2B
Context40,960
Weights4.1 GB
License
AccessOpen weights
Monthly Downloads363

Runs On

What it takes to serve DiStil-Qwen3-1.7B-uncensored (2B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 4.1 GB 4.9 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 2.0 GB 2.4 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 1.0 GB 1.2 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

Uncensored Distillation of Qwen3-1.7B — Alignment-Free Capability Transfer DiStil-Qwen3-1.7B-uncensored is a 1.7B parameter model produced by distilling Qwen3 with uncensored SFT data, removing alignment-imposed refusal behaviors while preserving the base model's reasoning and generation capabilities. The goal is a model that responds to the prompt as given rather than filtering through safety heuristics that often misfire on legitimate technical, analytical, and research queries. This is the base model in a distillation chain: - DiStil-Qwen3-1.7B-uncensored ← you are here - → Disctil-Qwen3-1.7B (DISC-informed refinement) Supervised fine-tuning using TRL on uncensored instruction data. The…

Excerpt from the card by Convergent Intelligence.

Configuration

Architecture
Qwen3ForCausalLM
Context length (tokens)
40,960
Layers
28
Hidden size
2,048
Feed-forward size
6,144
Attention heads
16
Key/value heads
8
Head dimension
128
Vocabulary size
151,936
Model type
qwen3

Identity and Version

Repository
reaperdoesntknow/DiStil-Qwen3-1.7B-uncensored
Publisher
Convergent Intelligence
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
2B parameters
Languages
Not stated by the source
Revision
31cc91965a23cfe832d089765f40381e6e0e4c42
First published
2026-03-28
Last updated
2026-09-18

Files and Weights

10 files, 4.1 GB in total. The weights are 1 file totalling 4.1 GB in safetensors.

Weights1 file · 4.1 GB
Configuration3 files · 152.1 KB
Tokenizer2 files · 11.4 MB
Documentation1 file · 5.6 KB
Other2 files · 205.7 KB
Repository1 file · 1.6 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights4.1 GB 120d82c4313a
config.jsonConfiguration1.4 KB
generation_config.jsonConfiguration187 B
trainer_state (2).jsonConfiguration150.5 KB
README.mdDocumentation5.6 KB
chat_template.jinjaOther4.2 KB
events.out.tfevents.1774711157.c23bde7bdfe8.10063.0Other201.5 KB ab24fbf638a3
.gitattributesRepository1.6 KB
tokenizer.jsonTokenizer11.4 MB be75606093db
tokenizer_config.jsonTokenizer665 B

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
4.1 GB
Download from Convergent Intelligence

Released by Convergent Intelligence through its official repository on Hugging Face.

Built From

Memory Requirements

PrecisionWeights in memory
As published4.1 GB
16-bit4.1 GB
8-bit2.0 GB
4-bit1.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Built on This Model

Questions About DiStil-Qwen3-1.7B-uncensored

How much GPU memory does DiStil-Qwen3-1.7B-uncensored need?

About 4.9 GB at 16-bit and 1.2 GB at 4-bit: the weights (2B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run DiStil-Qwen3-1.7B-uncensored on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

What is DiStil-Qwen3-1.7B-uncensored's context length?

40,960 tokens, from the maximum position embeddings in its published configuration.