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…
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.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also 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.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 4.1 GB | 120d82c4313a |
| config.json | Configuration | 1.4 KB | — |
| generation_config.json | Configuration | 187 B | — |
| trainer_state (2).json | Configuration | 150.5 KB | — |
| README.md | Documentation | 5.6 KB | — |
| chat_template.jinja | Other | 4.2 KB | — |
| events.out.tfevents.1774711157.c23bde7bdfe8.10063.0 | Other | 201.5 KB | ab24fbf638a3 |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 11.4 MB | be75606093db |
| tokenizer_config.json | Tokenizer | 665 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 4.1 GB
Released by Convergent Intelligence through its official repository on Hugging Face.
Built From
- Derived from reaperdoesntknow/TopologicalQwen
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 4.1 GB |
| 16-bit | 4.1 GB |
| 8-bit | 2.0 GB |
| 4-bit | 1.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Built on This Model
- Derived fromDualMind
- Derived fromDisctil-Qwen3-1.7B
- Derived fromDiscrepancy_Calculus
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.