Cipher 20B i1 needs about 15.3 GB of memory at Q4_K_M (a 12.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 4.8 GB (IQ1_S) to 16.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.3 GB.
Cipher 20B i1 – 20.6B parameter Qwen2 model for code generation
Cipher 20B i1 is a 20.6 billion parameter causal language model based on Qwen2. It is optimized for coding tasks and tool usage. The model supports a 32,768 token context window.
Good at
- Code generation in multiple languages
- Detecting and correcting coding errors
- Providing clear code explanations
Limits
- No vision support
- Large VRAM required for higher quant levels
- License is other, not standard
Best for
- Developers needing code assistance
- Automated code review tools
- Educational coding platforms
Who it’s for. Developers, educators, and researchers who need a large language model focused on code generation and debugging. The model is suitable for environments that can accommodate its memory requirements.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 4.8 GB | 7.6 GB | Tight | Get file → | |
| IQ1_M | 5.2 GB | 8.0 GB | Too big | Get file → | |
| IQ2_XXS | 5.8 GB | 8.7 GB | Too big | Get file → | |
| IQ2_XS | 6.4 GB | 9.2 GB | Too big | Get file → | |
| IQ2_S | 6.8 GB | 9.6 GB | Too big | Get file → | |
| IQ2_M | 7.3 GB | 10.1 GB | Too big | Get file → | |
| Q2_K_S | 7.4 GB | 10.2 GB | Too big | Get file → | |
| Q2_K | 7.9 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XXS | 8.2 GB | 11.0 GB | Too big | Get file → | |
| IQ3_XS | 8.7 GB | 11.6 GB | Too big | Get file → | |
| Q3_K_S | 9.1 GB | 12.0 GB | Too big | Get file → | |
| IQ3_S | 9.2 GB | 12.0 GB | Too big | Get file → | |
| IQ3_M | 9.5 GB | 12.3 GB | Too big | Get file → | |
| Q3_K_M | 10.1 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_L | 11.0 GB | 13.8 GB | Too big | Get file → | |
| IQ4_XS | 11.2 GB | 14.0 GB | Too big | Get file → | |
| Q4_0 | 11.8 GB | 14.6 GB | Too big | Get file → | |
| Q4_K_S | 11.8 GB | 14.7 GB | Too big | Get file → | |
| Q4_K_M | 12.4 GB | 15.3 GB | Too big | Get file → | |
| Q5_K_S | 14.2 GB | 17.1 GB | Too big | Get file → | |
| Q5_K_M | 14.6 GB | 17.4 GB | Too big | Get file → | |
| Q6_K | 16.9 GB | 19.7 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (file size 4.83 GB, estimated 7.6 GB memory). For 12‑GB VRAM, IQ2_M (file size 7.31 GB, estimated 10.1 GB memory) or Q2_K (file size 7.9 GB, estimated 10.7 GB memory). For 16‑GB VRAM, Q3_K_M (file size 10.12 GB, estimated 12.9 GB memory) or Q4_K_M (file size 12.44 GB, estimated 15.3 GB memory).
What GPU do you need for Cipher 20B i1?
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 IQ1_M (5.2 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_S (9.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (12.4 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (16.9 GB file, about 19.7 GB in use).
Which Cipher 20B i1 quant should you choose?
Q4_K_M is the usual starting point for Cipher 20B i1: it balances file size and quality well. Here it is a 12.4 GB file.
If memory is tight, the smallest file is IQ1_S at 4.8 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 Cipher 20B i1
How much VRAM does Cipher 20B i1 need?
About 15.3 GB at Q4_K_M with an 8K context window. That is the 12.4 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 Cipher 20B i1 on an 8 GB GPU?
Yes, with IQ1_M: the 5.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Cipher 20B i1 GGUF?
It depends on the quant: IQ1_S is 4.8 GB, IQ1_M is 5.2 GB, IQ2_XXS is 5.8 GB, IQ2_XS is 6.4 GB, IQ2_S is 6.8 GB, IQ2_M is 7.3 GB and 16 more.
What context length does Cipher 20B i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.3 GB at 32K.
Where can I download Cipher 20B i1 GGUF?
The files are on Hugging Face in the mradermacher/Cipher-20B-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 Cipher 20B i1 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 Cipher 20B i1 on 8 GB VRAM?
Yes, using the IQ1_S quant which requires about 7.6 GB of VRAM at 8k context.
Does Cipher 20B i1 support image inputs?
No, the model has no vision capabilities.
What is the maximum context length for this model?
The model supports up to 32,768 tokens.