CodeShell needs about 7.0 GB of memory at Q4_K_M (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 1.8 GB (IQ1_S) to 6.6 GB (Q6_K).
CodeShell – 7.98B parameter code LLM with 8192 token context
CodeShell is a 7.98B parameter code language model trained on 500B tokens. It supports 8192 token context and is optimized for code generation tasks. The model is available in multiple GGUF quantizations.
Good at
- Code generation
- Bug detection and repair
- Test case creation
Limits
- No vision support
- License not specified
- Requires 8k context for full performance
Best for
- Local IDE code assistance
- Automated code review
- Rapid prototyping
Who it’s for. Developers needing a local, code‑focused LLM for IDE integration or automated coding workflows. The model is suitable for teams that prefer open‑source tooling and local deployment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.8 GB | 3.7 GB | Fits | Get file → | |
| IQ1_M | 2.0 GB | 3.9 GB | Fits | Get file → | |
| IQ2_XXS | 2.2 GB | 4.1 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 4.4 GB | Fits | Get file → | |
| IQ2_S | 2.6 GB | 4.5 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 4.7 GB | Fits | Get file → | |
| Q2_K_S | 2.8 GB | 4.8 GB | Fits | Get file → | |
| Q2_K | 3.1 GB | 5.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.2 GB | 5.1 GB | Fits | Get file → | |
| IQ3_XS | 3.5 GB | 5.4 GB | Fits | Get file → | |
| IQ3_S | 3.5 GB | 5.5 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 5.5 GB | Fits | Get file → | |
| IQ3_M | 3.8 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_M | 4.2 GB | 6.1 GB | Fits | Get file → | |
| IQ4_XS | 4.3 GB | 6.2 GB | Fits | Get file → | |
| IQ4_NL | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q4_0 | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_L | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q4_K_S | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q4_1 | 5.0 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q5_K_S | 5.5 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 5.9 GB | 7.8 GB | Tight | Get file → | |
| Q6_K | 6.6 GB | 8.5 GB | Too big | Get file → |
For 8GB VRAM, use IQ1_S (1.84 GB) or IQ1_M (1.98 GB). If 16GB VRAM is available, Q4_K_M (5.06 GB) offers a good balance of size and performance. Larger quants such as Q6_K (6.55 GB) require more memory but provide higher fidelity.
What GPU do you need for CodeShell?
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 IQ1_M (2.0 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (3.8 GB file, about 5.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.5 GB in use).
Which CodeShell quant should you choose?
Q4_K_M is the usual starting point for CodeShell: it balances file size and quality well. Here it is a 5.1 GB file.
If memory is tight, the smallest file is IQ1_S at 1.8 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
Source
Frequently asked questions about CodeShell
How much VRAM does CodeShell need?
About 7.0 GB at Q4_K_M with an 8K context window. That is the 5.1 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 CodeShell on an 8 GB GPU?
Yes, with Q5_K_M: the 5.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of CodeShell GGUF?
It depends on the quant: IQ1_S is 1.8 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.2 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.
What context length does CodeShell support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.4 GB at 8K and 1.4 GB at 8K.
Where can I download CodeShell GGUF?
The files are on Hugging Face in the mradermacher/CodeShell-7B-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 CodeShell on 8GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which require about 3.7–3.9 GB at 8k context.
Does CodeShell support image inputs?
No, the model has no vision capabilities.