FI

Firefly v6 DONTDOWNLOAD STILLONPROGRESS

FireflyGGUF by mradermacherUpdated 2026-09-25
Download on Hugging Face
Parameters4.63B
Context128K
Layers35
Architecturegemma4
Smallest quant0.0 GB
Quick answer

Firefly v6 DONTDOWNLOAD STILLONPROGRESS needs about 4.5 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 25 quants, from 0.0 GB to 3.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Firefly v6 DONTDOWNLOAD STILLONPROGRESS – a 4.6B Gemma4 model with roleplay and tool use

Firefly v6 DONTDOWNLOAD STILLONPROGRESS is a 4.6 billion parameter Gemma4 model fine‑tuned for roleplay and tool usage. It is a text‑only LoRA merge, with vision and audio components frozen and untested. The model is experimental and not yet released for public use.

Good at

  • Roleplay interactions
  • Tool‑enabled responses
  • Text‑only fine‑tuning

Limits

  • No vision or audio support
  • Experimental release, no benchmark data
  • License terms not specified

Best for

  • Personal agentic chat
  • Tool‑driven task automation
  • Role‑playing scenarios

Who it’s for. Developers and researchers who need a lightweight, text‑only agent capable of roleplay and tool invocation. The model is suitable for experimentation and personal evaluation rather than production use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.1 GB
Fits Get file →
IQ1_S2.3 GB 3.4 GB
Fits Get file →
IQ1_M2.4 GB 3.4 GB
Fits Get file →
IQ2_XXS2.4 GB 3.5 GB
Fits Get file →
IQ2_XS2.5 GB 3.6 GB
Fits Get file →
IQ2_S2.5 GB 3.6 GB
Fits Get file →
IQ2_M2.6 GB 3.6 GB
Fits Get file →
IQ3_XXS2.6 GB 3.7 GB
Fits Get file →
Q2_K_S2.9 GB 4.0 GB
Fits Get file →
Q2_K3.0 GB 4.1 GB
Fits Get file →
IQ3_XS3.1 GB 4.1 GB
Fits Get file →
Q3_K_S3.1 GB 4.2 GB
Fits Get file →
IQ3_S3.1 GB 4.2 GB
Fits Get file →
IQ3_M3.1 GB 4.2 GB
Fits Get file →
Q3_K_M3.2 GB 4.3 GB
Fits Get file →
Q3_K_L3.3 GB 4.4 GB
Fits Get file →
IQ4_XS3.3 GB 4.4 GB
Fits Get file →
IQ4_NL3.4 GB 4.4 GB
Fits Get file →
Q4_03.4 GB 4.4 GB
Fits Get file →
Q4_K_S3.4 GB 4.4 GB
Fits Get file →
Q4_K_M3.4 GB 4.5 GB
Fits Get file →
Q4_13.5 GB 4.6 GB
Fits Get file →
Q5_K_S3.6 GB 4.7 GB
Fits Get file →
Q5_K_M3.6 GB 4.7 GB
Fits Get file →
Q6_K3.8 GB 4.9 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈3.4 GB memory). With 12 GB VRAM, Q2_K or Q2_K_S (≈4 GB). For 16 GB VRAM, Q3_K_M or Q4_K_M (≈4.5 GB). Memory estimates are approximate.

What GPU do you need for Firefly v6 DONTDOWNLOAD STILLONPROGRESS?

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 Q2_K_S (2.9 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 4.9 GB in use).

Which Firefly v6 DONTDOWNLOAD STILLONPROGRESS quant should you choose?

Q4_K_M is the usual starting point for Firefly v6 DONTDOWNLOAD STILLONPROGRESS: it balances file size and quality well. Here it is a 3.4 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma4
Parameters4.63B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Frequently asked questions about Firefly v6 DONTDOWNLOAD STILLONPROGRESS

How much VRAM does Firefly v6 DONTDOWNLOAD STILLONPROGRESS need?

About 4.5 GB at Q4_K_M with an 8K context window. That is the 3.4 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 Firefly v6 DONTDOWNLOAD STILLONPROGRESS on an 8 GB GPU?

Yes, with Q6_K: the 3.8 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Firefly v6 DONTDOWNLOAD STILLONPROGRESS GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.3 GB, IQ1_M is 2.4 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.5 GB and 19 more.

What context length does Firefly v6 DONTDOWNLOAD STILLONPROGRESS support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.3 GB at 32K.

Where can I download Firefly v6 DONTDOWNLOAD STILLONPROGRESS GGUF?

The files are on Hugging Face in the mradermacher/Firefly-v6-DONTDOWNLOAD-STILLONPROGRESS-i1-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 this model on 8 GB VRAM?

Yes, using IQ1_S or IQ1_M quantizations will fit within 8 GB VRAM with about 3.4 GB memory usage.

Does this model support vision or audio?

No, the vision and audio components are frozen and untested; the model is text‑only.

Is there a license for using this model?

No license information is provided; use only for personal evaluation and review source attribution files.

Other GGUFs of Firefly-v6-DONTDOWNLOAD-STILLONPROGRESS

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Firefly models

All Firefly →

Other small models

All small models →