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 25 quants, from 0.0 GB to 6.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
GhostShell 4B – a 7.46B Gemma‑4 based model with reasoning and tool use
GhostShell 4B is a 7.46B parameter Gemma‑4 variant tuned for reasoning and tool use. It is an ablated and instruction‑tuned model released by DuoNeural. The model is available in multiple GGUF quantizations.
Good at
- reasoning
- tool usage
- instruction following
Limits
- no vision support
- trained context 131072 tokens
- license gemma
Best for
- small‑to‑medium inference on GPUs
- research on reasoning tasks
- tool‑enabled applications
Who it’s for. Developers and researchers who need a Gemma‑4 based model with enhanced reasoning and tool usage. The model is experimental and should not be used in production without further testing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.9 GB | Fits | Get file → | |
| IQ1_S | 3.3 GB | 5.2 GB | Fits | Get file → | |
| IQ1_M | 3.4 GB | 5.3 GB | Fits | Get file → | |
| IQ2_XXS | 3.5 GB | 5.4 GB | Fits | Get file → | |
| IQ2_XS | 3.6 GB | 5.5 GB | Fits | Get file → | |
| IQ2_S | 3.7 GB | 5.6 GB | Fits | Get file → | |
| IQ2_M | 3.8 GB | 5.7 GB | Fits | Get file → | |
| IQ3_XXS | 4.0 GB | 5.9 GB | Fits | Get file → | |
| Q2_K_S | 4.3 GB | 6.2 GB | Fits | Get file → | |
| Q2_K | 4.4 GB | 6.3 GB | Fits | Get file → | |
| IQ3_XS | 4.5 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_S | 4.6 GB | 6.5 GB | Fits | Get file → | |
| IQ3_S | 4.6 GB | 6.5 GB | Fits | Get file → | |
| IQ3_M | 4.7 GB | 6.6 GB | Fits | Get file → | |
| Q3_K_M | 4.8 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_L | 5.0 GB | 6.9 GB | Fits | Get file → | |
| IQ4_XS | 5.0 GB | 6.9 GB | Fits | Get file → | |
| IQ4_NL | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q4_0 | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_S | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Tight | Get file → | |
| Q4_1 | 5.4 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_S | 5.6 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 6.2 GB | 8.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.30 GB, estimated 7.2 GB memory). For 12 GB VRAM, Q6_K (file size 6.17 GB, estimated 8.1 GB memory) is suitable. Smaller quants such as IQ1_S or IQ2_XXS reduce VRAM usage but increase 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: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XXS (4.0 GB file, about 5.9 GB in use).
- 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 Q6_K (6.2 GB file, about 8.1 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.
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
Source
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: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.4 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.6 GB, IQ2_S is 3.7 GB and 19 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-i1-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 GhostShell 4B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 7.2 GB VRAM at 8 k context, which fits in 8 GB VRAM with some headroom.
Does GhostShell 4B support vision?
No, the model is text‑only; no vision files are provided.
What is the maximum context length for inference?
The model was trained on 131072 tokens, so that is the maximum context length supported.