AEON-7 / text-generation updated 1 month ago

Gemma-4-E4B-DECKARD-HERETIC-NVFP4

Name: Gemma-4-E4B-DECKARD-HERETIC-NVFP4
Author: AEON-7

NVFP4-quantized EAGLE-style speculative-decoding drafter for the standard (non-uncensored) Gemma 4 31B DECKARD HERETIC. Pair with the matching target model for accelerated single-stream decode on Blackwell-class GPUs (DGX Spark / RTX PRO 6000 / RTX 5090 / B100 / B200).

Params

6.2 B

Context

—

Downloads 30d

217 K

Likes

Commercial use: conditional · gemma Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

248 K217 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	10.2 GB	12.6 GB	✅ Runs comfortably

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/gemma-4-e4b-deckard-heretic-nvfp4
{
  "hf_id": "AEON-7/Gemma-4-E4B-DECKARD-HERETIC-NVFP4",
  "params_b": 6.20,
  "context_length": null,
  "license": { "id": "gemma", "commercial": "conditional" },
  "downloads_30d": 217459,
  "vram_estimates": [
    { "quant": "bf16", "gb": 12.6 }
  ],
  "updated_at": "2026-07-28T18:07:18Z"
}

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

Specifications

Architecture: Gemma4ForConditionalGeneration
Parameters: 6.2 B
Tensor type: BF16
Licence: gemma
First seen on the Hub: 2026-04-13
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

Qwen3-8B 16.3 M Qwen2.5-7B-Instruct 12.1 M Qwen3.6-35B-A3B-NVFP4 11.3 M Llama-3.1-8B-Instruct 8.0 M Qwen2.5-7B-Instruct-AWQ 4.6 M Qwen3-4B 4.6 M

Appears in

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