# DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO GGUF URL: https://interfaze.ai/models/atomicchatdeepseek-v41-flash-1017-uncensored-gsq-rco-gguf [All models](https://interfaze.ai/models) DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO GGUF by AtomicChat, a text-generation model with multimodal capabilities. Understand and compare multimodal features, benchmarks, and capabilities. ## Comparison | Feature | DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO GGUF | Interfaze | | --- | --- | --- | | Input Modalities | text, image | image, text, audio, video, document | | Native OCR | No | Yes | | Long Document Processing | Yes | Yes | | Language Support | 338 partial | 162+ | | Native Speech-to-Text | No | Yes | | Native Object Detection | No | Yes | | Guardrail Controls | Yes | Yes | | Context Input Size | 1M | 1M | | Tool Calling | Yes | Tool calling supported + built in browser, code execution and web search | ### Scaling | Feature | DeepSeek V4.1 Flash 1017 Uncensored GSQ RCO GGUF | Interfaze | | --- | --- | --- | | Scaling | Self-hosted/Provider-hosted with quantization | Unlimited | [Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs) View model card on [Hugging Face](https://huggingface.co/AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF) - These are [ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF)'s GSQ-RCO backbone shards (revision `cb02422c900d`) with **only the residual-writing dense tensors replaced**: attention output (`attn_output_b`), the shared-expert down projection (`ffn_down_shexp`) and the Engram value projection (`engram_wkv`). The **routed experts are left exactly as ISTA shipped them**, so GSQ's learned low-bit rounding of the experts is preserved byte for byte, and each file stays the same size and runs wherever the original runs. - The replaced tensors carry the one-direction refusal edit (strength 2.0) baked into DeepSeek's weights at full precision and quantized to ISTA's exact per-tensor type. - Runs on a **single 12 GB GPU** with [Strata](https://github.com/Niko1221/Strata): the backbone sits in system memory and the shared **Engram table streams from an SSD**, so a 763B model fits a consumer machine. > Not every rung cleared every gate; such a rung is published as measured, with its numbers in the table and the metrics repo. ## What changed and what did not Both files served on Strata, same prompts and template; "→" reads the stock GSQ-RCO rung → this one. | Rung | bpw | Total GB | JailbreakBench (EN) | XSTest (safe refused) | Thinking high (30) | MMLU (500) | KL to stock | | --- | --- | --- | --- | --- | --- | --- | --- | | IQ2\_XXS | 2.0 | 249 | 85.2% → 0.0% | 7.6% → 0.0% | 27/30 → 0/30 | 82.8% (p=0.27) | 0.0225 | | IQ2\_XS | 2.25 | 266 | 86.4% → 0.0% | 4.0% → 0.4% | 27/30 → 2/30 | 81.6% (p=1.00) | 0.0272 | | IQ1\_M | 1.75 | 231 | 88.9% → 0.0% | 4.8% → 0.0% | 27/30 → 1/30 | 80.6% (p=0.75) | 0.0207 | KL is the edit's distribution shift from the stock rung, from Strata's teacher-forced score mode: a top-64 lower bound, so the true KL is a little higher. The shift is small enough (KL ~0.02, MMLU-500 within ~1 pt of the stock quant) that the GSQ-RCO quant's task accuracy is preserved — see the reasoning benchmarks below. Measurements, prompts and gates: [AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF-metrics](https://huggingface.co/datasets/AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF-metrics) (`ablit/gsq/`). ## Reasoning is preserved The uncensored edit changes only the dense residual writers (attention output, shared-expert FFN-down, Engram value); the 384 GSQ-learned routed-expert layers are left byte-for-byte intact. We benchmarked the edited IQ2\_XXS rung against the stock GSQ-RCO quant on the same stand (Strata, reasoning effort 50): | Benchmark | Stock GSQ-RCO | Uncensored (ours) | | --- | --- | --- | | GPQA-Diamond (198 q) | 83.3% | 83.3% | | AIME25 (30 q) | 76.7% | 80.0% | GPQA-Diamond is identical and AIME25 is a hair higher (within noise at n=30): abliteration done this way costs no task accuracy. Per-question logs: [metrics repo](https://huggingface.co/datasets/AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF-metrics) (`ablit/gsq/bench/`). ## Running it Download one rung and ISTA-DASLab's shared Engram file, then serve with Strata: ``` hf download AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GSQ-RCO-GGUF --include "*IQ2_XXS*" --local-dir ds-unc hf download ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF --include "*Engram*" --local-dir ds-unc # the 110 GB lookup table, once strata launch --model-path ds-unc/DeepSeek-V4.1-Flash-1017-GSQ-RCO-IQ2_XXS-00001-of-00004.gguf ``` The Engram file is identical to ISTA-DASLab's and is **not** re-hosted here; keep it on a fast SSD next to the shards. As of this writing these files run in Strata (DeepSeek-V4.1 with a separate Engram file is not yet in llama.cpp). ## Limitations - The refusal classifier reads the start of an answer, so a soft refusal later in the text can pass as an answer. - The edit removes refusals across topics; it does not keep a narrower set of them. - With thinking on, the edit plans an answer to a request the original declines, and the plan can be long; give such requests a larger token budget or a lower effort. ## Responsible use This model answers requests the original declines. You are responsible for how you use it and for following the laws that apply to you. ## Credits and license - Base model: [deepseek-ai/DeepSeek-V4.1-Flash-1017](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) — MIT (its LICENSE ships here). - GSQ-RCO quantization and the shared Engram file: [ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF](https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF) (DASLab, IST Austria). - Runtime: [Strata](https://github.com/Niko1221/Strata). MIT, as the base model and ISTA-DASLab's GGUFs. Built by AtomicChat. ## Want more deterministic results? [Try Interfaze](https://interfaze.ai/dashboard)[Read the Docs](https://interfaze.ai/docs)