FI

Firefly v4

FireflyGGUF by mradermacherUpdated 2026-10-29
Download on Hugging Face
Parameters4.65B
Context128K
Layers35
Architecturegemma4
Smallest quant3.0 GB
Quick answer

Firefly v4 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 12 quants, from 3.0 GB (Q2_K) to 9.3 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.3 GB.

Firefly v4 – uncensored multimodal LLM with vision, audio, and switchable reasoning

Firefly v4 is a 4.65 billion‑parameter Gemma4 model fine‑tuned with Unsloth. It supports text, vision, and audio natively and offers a toggle for chain‑of‑thought reasoning. The model is designed for immersive role‑play and creative writing without alignment guardrails.

Good at

  • Uncensored role‑play
  • Native vision and audio processing
  • Switchable reasoning

Limits

  • No vision or audio support on older hardware
  • Requires at least 8 k context for estimates
  • License is attribution only

Best for

  • Interactive storytelling
  • Creative writing with multimodal prompts
  • Rapid prototyping of role‑play scenarios

Who it’s for. Developers and creators who need a fully open, multimodal LLM for role‑play and creative tasks. The model is suitable for personal projects and research where unrestricted output is desired.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K3.0 GB 4.1 GB
Fits Get file →
Q3_K_S3.1 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 →
Q4_K_S3.4 GB 4.5 GB
Fits Get file →
Q4_K_M3.4 GB 4.5 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 →
Q8_05.0 GB 6.1 GB
Fits Get file →
F169.3 GB 10.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (3.43 GB) or Q5_K_M (3.63 GB). If 16 GB VRAM is available, Q6_K (3.85 GB) or Q8_0 (4.97 GB) provide higher quality. Larger models like F16 (9.31 GB) need 10.4 GB memory at 8 k context.

What GPU do you need for Firefly v4?

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: no quant fits at an 8K context.
  • 6 GB VRAM: the best quant that fits is Q6_K (3.8 GB file, about 4.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (9.3 GB file, about 10.4 GB in use).

Which Firefly v4 quant should you choose?

Q4_K_M is the usual starting point for Firefly v4: it balances file size and quality well. Here it is a 3.4 GB file.

The Q8_0 file is 5.0 GB, about 1.4 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 3.0 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

Architecturegemma4
Parameters4.65B
Layers35
Trained context131,072 tokens
KV cache (fp16)70 KB per token

Source

Quantized bymradermacher
FamilyFirefly
Licenseother
Downloads (HF)712
Last updated2026-10-29

Frequently asked questions about Firefly v4

How much VRAM does Firefly v4 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 v4 on an 8 GB GPU?

Yes, with Q8_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Firefly v4 GGUF?

It depends on the quant: Q2_K is 3.0 GB, Q3_K_S is 3.1 GB, Q3_K_M is 3.2 GB, Q3_K_L is 3.3 GB, IQ4_XS is 3.3 GB, Q4_K_S is 3.4 GB and 6 more.

What context length does Firefly v4 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 v4 GGUF?

The files are on Hugging Face in the mradermacher/Firefly-v4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Firefly v4 use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Firefly v4 on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 4.5 GB memory at 8 k context, which fits within 8 GB VRAM.

Does Firefly v4 support vision?

Yes, it natively understands images as part of a conversation.

Is there a reasoning toggle?

Yes, prefix the prompt with <|think|> to enable chain‑of‑thought reasoning.

Other GGUFs of Firefly-v4

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Firefly models

All Firefly →

Other small models

All small models →