GH

GhostShell 4B

GhostshellGGUF by mradermacherUpdated 2026-10-07
Download on Hugging Face
Parameters7.46B
Context128K
Layers42
Architecturegemma4
Smallest quant4.4 GB
Quick answer

GhostShell 4B needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 12 quants, from 4.4 GB (Q2_K) to 14.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

GhostShell 4B – a 7.46B Gemma4 model with reasoning and tools support

GhostShell 4B is a 7.46B parameter Gemma4 model tuned for reasoning and tool usage. It is an ablated and instruction‑tuned variant of google/gemma-4-e4b-it, released as an early, untested model. The model supports a 131072 token context window.

Good at

  • Reasoning
  • Tool usage
  • Instruction following

Limits

  • Early release, untested in production
  • No vision support
  • Large VRAM requirement for higher quants

Best for

  • Local inference on high‑VRAM GPUs
  • Tool‑enabled applications
  • Research on Gemma4 architecture

Who it’s for. Developers and researchers who need a Gemma4‑based model with reasoning and tool capabilities, and who are comfortable experimenting with an early release. The model is suitable for local deployment on systems with sufficient VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.4 GB 6.3 GB
Fits Get file →
Q3_K_S4.6 GB 6.5 GB
Fits Get file →
Q3_K_M4.8 GB 6.7 GB
Fits Get file →
Q3_K_L5.0 GB 6.9 GB
Fits Get file →
IQ4_XS5.1 GB 7.0 GB
Fits Get file →
Q4_K_S5.2 GB 7.1 GB
Fits Get file →
Q4_K_M5.3 GB 7.2 GB
Tight Get file →
Q5_K_S5.6 GB 7.6 GB
Tight Get file →
Q5_K_M5.7 GB 7.6 GB
Tight Get file →
Q6_K6.2 GB 8.1 GB
Too big Get file →
Q8_08.0 GB 9.9 GB
Too big Get file →
F1614.9 GB 16.9 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 5.3 GB, estimated 7.2 GB memory). For 12 GB VRAM, Q8_0 (file size 7.97 GB, estimated 9.9 GB memory) is appropriate. Higher precision quants like F16 require 16.9 GB memory and 14.94 GB file size.

What GPU do you need for GhostShell 4B?

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: no quant fits at an 8K context.
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.0 GB file, about 9.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (14.9 GB file, about 16.9 GB in use).

Which GhostShell 4B quant should you choose?

Q4_K_M is the usual starting point for GhostShell 4B: it balances file size and quality well. Here it is a 5.3 GB file.

The Q8_0 file is 8.0 GB, about 1.5 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 4.4 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
Parameters7.46B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized bymradermacher
Licensegemma
Downloads (HF)119
Last updated2026-10-07

Frequently asked questions about GhostShell 4B

How much VRAM does GhostShell 4B need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 GhostShell 4B on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of GhostShell 4B GGUF?

It depends on the quant: Q2_K is 4.4 GB, Q3_K_S is 4.6 GB, Q3_K_M is 4.8 GB, Q3_K_L is 5.0 GB, IQ4_XS is 5.1 GB, Q4_K_S is 5.2 GB and 6 more.

What context length does GhostShell 4B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download GhostShell 4B GGUF?

The files are on Hugging Face in the mradermacher/GhostShell-4B-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 GhostShell 4B use?

Hugging Face lists the license as gemma. 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 Q4_K_M on 8 GB VRAM?

Yes, Q4_K_M requires approximately 7.2 GB memory at 8 k context, fitting within an 8 GB VRAM budget.

What is the context length of GhostShell 4B?

The model supports a 131072 token context window.

Is GhostShell 4B suitable for vision tasks?

No, the model does not include vision support.

Other GGUFs of GhostShell-4B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Ghostshell models

All Ghostshell →

Other small models

All small models →