Bahushruth / text-generation updated 1 month ago

Qwen3.6-35B-A3B-abliterated-v4

Name: Qwen3.6-35B-A3B-abliterated-v4
Author: Bahushruth

Uncensored version of Qwen/Qwen3.6-35B-A3B with refusal behavior removed via abliteration (norm-preserving orthogonalization).

Params

34.7 B

Context

262,144

Downloads 30d

916 K

Likes

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

916 K630 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	bf16	69.3 GB	82.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 256K ctx	69.3 GB	243.1 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-6-35b-a3b-abliterated-v4
{
  "hf_id": "Bahushruth/Qwen3.6-35B-A3B-abliterated-v4",
  "params_b": 34.66,
  "context_length": 262144,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 916039,
  "vram_estimates": [
    { "quant": "bf16", "gb": 82.0 }
  ],
  "updated_at": "2026-07-28T18:04:33Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Specifications

Architecture: Qwen3_5MoeForCausalLM
Parameters: 34.7 B
Tensor type: BF16
Context length: 262,144
Vocabulary: 248,320
Layers / heads: 40 / 16
Licence: apache-2.0
First seen on the Hub: 2026-06-11
Base model: Qwen3.6-35B-A3B
Training datasets: Bahushruth/abliteration-harmful-enriched, mlabonne/harmless_alpaca
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Base Qwen3.6-35B-A3B Qwen 5.9 M

Compare with

Qwen3.6-35B-A3B-NVFP4 11.3 M gpt-oss-20b 8.6 M Qwen3-32B 8.3 M dolphin-2.9.1-yi-1.5-34b 4.6 M OTel-2.0-LLM-31B-IT 3.3 M Qwen3-30B-A3B 3.1 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB