← back to catalog · registered 2026-11-20 05:04

bakon3/DeepSeek-V4.1-Flash-1017-IQ2XXS-vision-uncensored-rad

bakon3 Deepseek multimodal
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/bakon3%2FDeepSeek-V4.1-Flash-1017-IQ2XXS-vision-uncensored-rad"
Response includes
  • classification m-uncensored
  • files 6
  • author_summary 2 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
0
Likes
0
Model age
2d ago
created 2026-11-20
Downloads over time
Now 0 → from 0 ↑ 0%
0011 0 on Nov 20 0 on Nov 22 Nov
Nov 20 → Nov 22 · 3 snapshots · spans 2 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.

Metadata

License
mit
Tags
radiance rocm amd rdna4 deepseek deepseek-v4.1 uncensored abliterated tp4 iq2_xxs vision image-text-to-text

Related

Control vectors

Total size
0 B
Files
6
Quantizations
1
Registered
2026-11-20 05:04
Last updated on HF
2026-11-21 03:24

Files by quantization

Auxiliary files 6 files 188 KB
expert-stats.json 158 KB 4aebf046 download
chat_template.jinja 18.6 KB aca65cf6 download
README.md 4.51 KB 87b2486b download
RUNNING.md 3.76 KB 90852998 download
.gitattributes 1.48 KB a6344aac download
prepare-model.sh 1.19 KB df5f5b69 download

README current version from Hugging Face


license: mit
library_name: radiance
pipeline_tag: image-text-to-text
tags:

  • radiance
  • rocm
  • amd
  • rdna4
  • deepseek
  • deepseek-v4.1
  • uncensored
  • abliterated
  • tp4
  • iq2_xxs
  • vision
    base_model:
  • deepseek-ai/DeepSeek-V4.1-Flash-1017

DeepSeek-V4.1-Flash-1017 — IQ2_XXS vision, uncensored

DeepSeek-V4.1-Flash-1017 as a single .rad container for the radiance inference engine (AMD RDNA4, ROCm), with the release's 32-layer vision encoder kept as bf16 so images are accepted through the chat API. The refusal direction is edited out of 18 attention-output projections.

Weights are in this repo.

Container size: 259.09 GiB (278,197,639,056 bytes).

Container 259.09 GiB / 278,197,639,056 bytes
Files deepseek-v4.1-flash-1017-iq2xxs-vision-uncensored.rad.part-00 … .part-05 — six parts (45 GiB each, last 34.09 GiB; the Hub's per-file limit is 50 GB)
Reassemble cat deepseek-v4.1-flash-1017-iq2xxs-vision-uncensored.rad.part-0[0-5] > deepseek-v4.1-flash-1017-iq2xxs-vision-uncensored.rad (sha256 77c5d2e021af59e374e368a8b1f05d145bb4f1a2fe6f687c64e39236b167cfb0)
Base DeepSeek-V4.1-Flash-1017 (fp8 weights, fp4 routed experts; MIT)
Routed experts IQ2_XXS (iq2_xxs, ≈2.06 bits/weight) on every routed-expert layer
Attention q6_K on layers 0–26, q5_K on layers 27–39; DSpark layers 40–42 bf16
Shared experts q6_K and q8_0
Engram table iq4_nl, 103 GiB, rebuilt from the release tokenizer; the release ships no Engram table
Embeddings / output q6_K
Vision encoder bf16; 32 blocks, hidden 1024, 16 heads of width 64, patch 14, 2D RoPE, 3×3 aligner; 0.904 GiB as stored
DSpark drafter MXFP4 experts as released, 6.72 GiB
Abliteration attn_output_b of layers 11–28, alpha 0.75; the other 18 layers stay stock
Norms / routers f32
Measured 56.9 tok/s decode (256 tokens), 24,013-token prompt TTFT 7.03 s on four 32 GB RDNA4 cards, TP4, n-gram 5 speculation

Run it today: upstream main does not carry the arch/deepseek41 plugin yet. Clone the deepseek41-wip branch of bakon/radiance and build it. The download, join, build and serve commands are in RUNNING.md.

Quantisation

This is a per-tensor mix, not one global type. The routed experts were re-quantised from the official checkpoint with the IQ2_XXS search; the attention, shared experts, embedding and output planes stay at their higher-width quantisers; the vision encoder is bf16. The 259 vision tensors, four aligner tensors, three delimiter vectors and 43 bias_vl vectors were appended after conversion; the IQ2-only file cannot see images.

iq2_xxs, q6_K, q5_K, q8_0 and iq4_nl are the canonical GGML encodings. The DSpark experts keep the release's MXFP4 (fp4_e2m1 with e8m0 scales).

Vision path

Images enter through image content parts on /v1/chat/completions, the same OpenAI-compatible API as text. The chat template is in chat_template.jinja; the container must be served with --override-chat-template /models/chat_template.jinja.

The encoder is the release's own 32-block ViT and 3×3 aligner, kept bf16. Images are prefill-only and capped at 1,024 image tokens per image. The text path is the same IQ2_XXS model.

Serving

Hardware: four AMD Radeon AI PRO R9700 (gfx1201) cards, 32 GiB each; ROCm 10.1+; 64 GiB host RAM; the 259 GiB container and its 103 GiB Engram table on NVMe. The exact command, including --host-pool-mib 57344, --ngram-placement disk, --num-speculative-tokens 5 and --kv-cache-dtype fp8, is in RUNNING.md.

The server speaks OpenAI's chat API (/v1/chat/completions, /v1/models); the served model name is DeepSeek-V4.1-Flash.

Other radiance containers

Index: DeepSeek-V4.1-Flash radiance

Licence

DeepSeek-V4.1-Flash-1017 is MIT licensed (Copyright © DeepSeek). This container is a modified copy: the routed experts and linears are re-encoded as the quantisers above, the Engram table is generated from the tokenizer, the vision encoder is included at bf16, and 18 attention-output projections carry the abliteration edit. MIT applies to the original and to these modifications.

README history 1 version

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

  1. 2026-11-20 Model card, run guide, chat template and expert profile a4400ef 4.5 KB
    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