GE

gemma4 12B it DFlash

GemmaGGUF by AnbeeldUpdated 2026-10-10
Download on Hugging Face
Parameters727M
Context256K
Layers5
Architecturedflash
Smallest quant0.3 GB
Quick answer

gemma4 12B it DFlash needs about 1.1 GB of memory at Q4_K_M (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 7 quants, from 0.3 GB (Q2_K) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.

Gemma 4 12B IT DFlash draft quantizations for BeeLlama.cpp

Gemma 4 12B IT DFlash is a draft model that uses block diffusion to draft multiple tokens in parallel. It is not a standalone Gemma 4 12B model and must be paired with google/gemma-4-12b-it. The GGUF files are quantized by Anbeeld and use BeeLlama.cpp for advanced quantization.

Good at

  • Reasoning
  • Tools usage
  • Parallel token drafting

Limits

  • Not a standalone model
  • No vision support
  • No license specified

Best for

  • Integrating with google/gemma-4-12b-it
  • Testing DFlash draft methods
  • Low‑memory inference

Who it’s for. Developers and researchers who want to experiment with DFlash draft models and need a lightweight quantized version for BeeLlama.cpp. The model is suitable for those who already have the target Gemma 4 12B IT model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.3 GB 1.0 GB
Fits Get file →
Q3_K_M0.4 GB 1.0 GB
Fits Get file →
Q4_K_M0.4 GB 1.1 GB
Fits Get file →
Q5_K_M0.5 GB 1.2 GB
Fits Get file →
Q6_K0.6 GB 1.3 GB
Fits Get file →
Q8_00.8 GB 1.5 GB
Fits Get file →
BF161.5 GB 2.1 GB
Fits Get file →

For 8 GB VRAM, Q4_K_M (0.44 GB) or Q5_K_M (0.52 GB) are recommended, as they use about 1.1–1.2 GB memory at 8 k context. For tighter budgets, Q2_K (0.28 GB) or Q3_K_M (0.36 GB) use around 1 GB memory. BF16 (1.47 GB) requires the most memory.

What GPU do you need for gemma4 12B it DFlash?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is BF16 (1.5 GB file, about 2.1 GB in use).

Which gemma4 12B it DFlash quant should you choose?

Q4_K_M is the usual starting point for gemma4 12B it DFlash: it balances file size and quality well. Here it is a 0.4 GB file.

The Q8_0 file is 0.8 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 0.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedflash
Parameters727M
Layers5
Trained context262,144 tokens
KV cache (fp16)20 KB per token

Source

Quantized byAnbeeld
FamilyGemma
Downloads (HF)832
Last updated2026-10-10

Frequently asked questions about gemma4 12B it DFlash

How much VRAM does gemma4 12B it DFlash need?

About 1.1 GB at Q4_K_M with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run gemma4 12B it DFlash on an 8 GB GPU?

Yes, with BF16: the 1.5 GB file needs about 2.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of gemma4 12B it DFlash GGUF?

It depends on the quant: Q2_K is 0.3 GB, Q3_K_M is 0.4 GB, Q4_K_M is 0.4 GB, Q5_K_M is 0.5 GB, Q6_K is 0.6 GB, Q8_0 is 0.8 GB and 1 more.

What context length does gemma4 12B it DFlash support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.

Where can I download gemma4 12B it DFlash GGUF?

The files are on Hugging Face in the Anbeeld/gemma4-12B-it-DFlash-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Gemma 4 12B IT DFlash on 8 GB VRAM?

Yes, using Q4_K_M or Q5_K_M quantizations will use about 1.1–1.2 GB memory at 8 k context, fitting within 8 GB VRAM.

Do I need the target Gemma 4 12B IT model to use these drafts?

Yes, the draft model must be paired with google/gemma-4-12b-it to function.

Which quantization is best for the lowest memory usage?

Q2_K (0.28 GB) uses the least memory, around 1 GB at 8 k context, but offers lower precision.

Other GGUFs of gemma4-12B-it-DFlash

Similar models

Browse all →

More from Anbeeld

All by Anbeeld →

More Gemma models

All Gemma →

Other tiny models

All tiny models →