StyleTune for your QAT model — without training anything.

Gemma-4-26B-A4B-QAT-StyleTune-V2-Voice

Google's QAT base + Gryphe's StyleTune voice. Best of both. One 1.5 GB download. Zero extra models.

This voice is cast from Gryphe/Gemma-4-26B-A4B-StyleTune-V2 and matched to Google's QAT checkpoint — google/gemma-4-26B-A4B-it-qat-q4_0-unquantized. If your GGUF is built from the QAT weights, this is the variant that fits it exactly.

---

Why QAT + StyleTune is the good combo

Two independent optimizations, now combined:

Google's QAT trains the model to survive quantization. Per Google, QAT gives 54% less perplexity drop at Q4_0 versus standard post-training quantization (Google Developers Blog) — 5,000 steps of fake-quantized forward passes with KL divergence to the BF16 teacher. Your Q4_0 GGUF keeps noticeably more of the original model's fidelity.

StyleTune then changes how it writes: per Gryphe's benchmarks — 200 roleplay prompts, greedy 0.0 — 52% fewer clichés (1.141 → 0.551 per 100 words) and only 19.9% shared trigram vocabulary vs the base instruct.

The old tradeoff was: QAT model or StyleTune model, pick one. Now you don't pick. If you already have a QAT GGUF, this voice turns it into a QAT-fidelity, StyleTune-voiced model — and you download 1.5 GB instead of 50+ GB.

---

Two steps

# 1. Get the voice tool (one-time): https://huggingface.co/Wiself/voice
python3 voice.py path

# 2. Cast onto your QAT-derived GGUF
voice cast ./gemma-4-26b-a4b-it-qat-q4_0-Q4_0.gguf voice.safetensors --out ./voiced/gemma-4-26b-a4b-qat-styletune.gguf

Run it:

llama serve -m ./voiced/gemma-4-26b-a4b-qat-styletune.gguf --jinja

No QAT finetune was needed. No extra model was downloaded. Your model, smarter voice, less quantization loss.

---

Why the QAT-matched variant exists

The QAT checkpoint's lm_head weights differ slightly from the standard instruct's (that's the point of QAT — the weights learned to live with quantization). This voice is cast as a delta against the normal google/gemma-4-26B-A4B-it (voice − base where base is the standard instruct, not QAT). When you later do delta + QAT_head → Q8_0, you add StyleTune's style to the QAT head — correct math, matched foundation.

Your GGUF is built from	Use
google/gemma-4-26B-A4B-it (standard)	V2 voice
google/gemma-4-26B-A4B-it-qat-q4_0-unquantized	this voice

---

The abliterated case (why we recommend delta by default here)

The most popular QAT-adjacent models are abliterated/uncensored variants — for example llmfan46/gemma-4-26B-A4B-it-qat-q4_0-unquantized-uncensored-heretic. We tested this exact pairing:

• Direct cast looped — repetitive output, unusable.
• Delta cast (voice delta → voice cast with the delta) — clean output, no loops, StyleTune phrasing intact.

On abliterated or heavily modified targets, start with the delta path (base is the normal instruct — correct math):

voice delta voice.safetensors --base google/gemma-4-26B-A4B-it
voice cast ./model.gguf delta-voice.safetensors --out ./voiced/model.gguf

Why it works: a delta carries only the difference from the base head, so the shift to MoE routing is minimal. Tiny nudges can flip which expert fires next in MoE models; the delta keeps the nudge small while keeping the style. Full story in the Voice tool card.

---

What's inside

• voice.safetensors — the style delta (voice − base), F16, shape [262144, 2816], ~1.5 GB
• voice.json — metadata: source, dtype, shape, base

---

Compatibility

Target	Works?
QAT-derived Gemma 4 26B A4B GGUFs (any quant)	✅ primary target
Abliterated QAT variants (heretic et al.)	✅ via the delta path above
Standard (non-QAT) 26B A4B GGUFs	✅ works, but the V2 voice is the exact match
Gemma 4 other sizes / non-Gemma	❌ shape mismatch

---

Notes

• Casting quantizes only the head to Q8_0 (near-lossless); every other tensor is byte-copied from your model — your QAT weights stay QAT weights.
• Sampler tips from Gryphe: temp 1.0, MinP 0.10, DRY sampler on. Gemma 4's native chat template applies automatically.
• Verify: voice info voice.safetensors → [262144, 2816] · F16 (delta marker present).

---

References & Credits

• QAT: Google Developers Blog — Gemma 3 Quantization-Aware Training — 54% less perplexity drop at Q4_0; checkpoint google/gemma-4-26B-A4B-it-qat-q4_0-unquantized, Gemma terms.
• StyleTune: Gryphe/Gemma-4-26B-A4B-StyleTune-V2 — 52% cliché reduction, 19.9% shared trigram vocabulary; Anthracite, Latitude.
• Tool: Voice — lift a voice, cast it onto any compatible GGUF.