Qwen2.5 Godzilla Coder V2 51B needs about 34.6 GB of memory at Q4_K_M (a 30.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 23 quants, from 11.0 GB (IQ1_S) to 41.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 13.6 GB.
Qwen2.5 Godzilla Coder V2 51B – a large coding‑focused model
Qwen2.5 Godzilla Coder V2 51B is a 51‑billion‑parameter model designed for code generation. It supports a 32768‑token context window and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- Code generation
- Large context handling
- High‑parameter density
Limits
- No vision support
- Requires large VRAM for full precision
- License is apache‑2.0
Best for
- Developers needing long‑context code assistance
- Researchers testing large‑scale coding models
- Teams building code‑generation tools
Who it’s for. The model is suited for developers, researchers, and teams that require extensive code generation capabilities and can allocate sufficient GPU memory. It is ideal for projects that can handle the model’s licensing terms and memory demands.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 11.0 GB | 14.9 GB | Too big | Get file → | |
| IQ1_M | 12.0 GB | 15.9 GB | Too big | Get file → | |
| IQ2_XXS | 13.8 GB | 17.7 GB | Too big | Get file → | |
| IQ2_XS | 15.3 GB | 19.1 GB | Too big | Get file → | |
| IQ2_S | 15.9 GB | 19.8 GB | Too big | Get file → | |
| IQ2_M | 17.3 GB | 21.1 GB | Too big | Get file → | |
| Q2_K_S | 17.6 GB | 21.5 GB | Too big | Get file → | |
| Q2_K | 18.9 GB | 22.8 GB | Too big | Get file → | |
| IQ3_XXS | 19.8 GB | 23.6 GB | Too big | Get file → | |
| IQ3_XS | 21.1 GB | 24.9 GB | Too big | Get file → | |
| Q3_K_S | 22.1 GB | 26.0 GB | Too big | Get file → | |
| IQ3_S | 22.2 GB | 26.1 GB | Too big | Get file → | |
| IQ3_M | 22.8 GB | 26.7 GB | Too big | Get file → | |
| Q3_K_M | 24.6 GB | 28.5 GB | Too big | Get file → | |
| Q3_K_L | 26.7 GB | 30.5 GB | Too big | Get file → | |
| IQ4_XS | 27.3 GB | 31.2 GB | Too big | Get file → | |
| Q4_0 | 28.9 GB | 32.8 GB | Too big | Get file → | |
| Q4_K_S | 29.0 GB | 32.9 GB | Too big | Get file → | |
| Q4_K_M | 30.7 GB | 34.6 GB | Too big | Get file → | |
| Q4_1 | 31.9 GB | 35.8 GB | Too big | Get file → | |
| Q5_K_S | 35.0 GB | 38.9 GB | Too big | Get file → | |
| Q5_K_M | 36.0 GB | 39.9 GB | Too big | Get file → | |
| Q6_K | 41.7 GB | 45.6 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 11.01 GB, estimated 14.9 GB memory). For 12 GB VRAM, IQ1_M (12.05 GB, 15.9 GB). For 16 GB VRAM, IQ2_S (15.87 GB, 19.8 GB). Larger VRAM allows higher‑quality quants such as Q4_K_M or Q5_K_M.
What GPU do you need for Qwen2.5 Godzilla Coder V2 51B?
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: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ1_M (12.0 GB file, about 15.9 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_XXS (19.8 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is IQ4_XS (27.3 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (41.7 GB file, about 45.6 GB in use).
Which Qwen2.5 Godzilla Coder V2 51B quant should you choose?
Q4_K_M is the usual starting point for Qwen2.5 Godzilla Coder V2 51B: it balances file size and quality well. Here it is a 30.7 GB file.
If memory is tight, the smallest file is IQ1_S at 11.0 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
Frequently asked questions about Qwen2.5 Godzilla Coder V2 51B
How much VRAM does Qwen2.5 Godzilla Coder V2 51B need?
About 34.6 GB at Q4_K_M with an 8K context window. That is the 30.7 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 Qwen2.5 Godzilla Coder V2 51B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwen2.5 Godzilla Coder V2 51B GGUF?
It depends on the quant: IQ1_S is 11.0 GB, IQ1_M is 12.0 GB, IQ2_XXS is 13.8 GB, IQ2_XS is 15.3 GB, IQ2_S is 15.9 GB, IQ2_M is 17.3 GB and 17 more.
What context length does Qwen2.5 Godzilla Coder V2 51B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 3.4 GB at 8K and 13.6 GB at 32K.
Where can I download Qwen2.5 Godzilla Coder V2 51B GGUF?
The files are on Hugging Face in the mradermacher/Qwen2.5-Godzilla-Coder-V2-51B-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 Qwen2.5 Godzilla Coder V2 51B use?
Hugging Face lists the license as apache-2.0. 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 this model on 8 GB VRAM?
Use the IQ1_S quant, which requires about 14.9 GB of VRAM at 8k context. It is the smallest quant available.
Does this model support image input?
No, the model is purely text‑based and does not support vision.
What license applies to this model?
The model is released under the apache‑2.0 license.