codegemma-1.1-7b-it needs about 9.6 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 4.1 GB (IQ3_M) to 9.1 GB (Q8_0).
CodeGemma 1.1 7b Instruct – a code‑focused Gemini model
CodeGemma 1.1 7b Instruct is a 8.54 billion‑parameter Gemma model fine‑tuned for code generation and mathematical reasoning. It builds on the original CodeGemma with minor improvements and a 80% code, 20% natural language mix.
Good at
- Code generation
- Mathematical reasoning
- Instruct‑style interactions
Limits
- No vision support
- License is gemma
- Context limited to 8192 tokens
Best for
- Writing scripts
- Debugging assistance
- Generating documentation
Who it’s for. Developers and programmers seeking a lightweight coding companion. The model is suitable for environments with limited GPU memory, as it offers several quantized variants.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_M | 4.1 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_L | 4.7 GB | 9.0 GB | Too big | Get file → | |
| IQ4_NL | 5.0 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_M | 5.3 GB | 9.6 GB | Too big | Get file → | |
| Q5_K_M | 6.1 GB | 10.4 GB | Too big | Get file → | |
| Q6_K | 7.0 GB | 11.3 GB | Too big | Get file → | |
| Q8_0 | 9.1 GB | 13.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_M (4.11 GB file, ~8.4 GB memory at 8k context). If 12 GB is available, Q4_K_M (5.33 GB file, ~9.6 GB memory) offers better quality. Larger VRAM allows Q5_K_M or Q6_K for higher fidelity.
What GPU do you need for codegemma-1.1-7b-it?
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: the best quant that fits is Q6_K (7.0 GB file, about 11.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.1 GB file, about 13.3 GB in use).
Which codegemma-1.1-7b-it quant should you choose?
Q4_K_M is the usual starting point for codegemma-1.1-7b-it: it balances file size and quality well. Here it is a 5.3 GB file.
The Q8_0 file is 9.1 GB, about 1.7 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 IQ3_M at 4.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about codegemma-1.1-7b-it
How much VRAM does codegemma-1.1-7b-it need?
About 9.6 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 codegemma-1.1-7b-it on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of codegemma-1.1-7b-it GGUF?
It depends on the quant: IQ3_M is 4.1 GB, Q3_K_L is 4.7 GB, IQ4_NL is 5.0 GB, Q4_K_M is 5.3 GB, Q5_K_M is 6.1 GB, Q6_K is 7.0 GB and 1 more.
What context length does codegemma-1.1-7b-it support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.8 GB at 8K and 3.8 GB at 8K.
Where can I download codegemma-1.1-7b-it GGUF?
The files are on Hugging Face in the lmstudio-community/codegemma-1.1-7b-it-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 codegemma-1.1-7b-it 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 CodeGemma 1.1 7b on 8 GB VRAM?
Yes, the IQ3_M quantized file is 4.11 GB and requires about 8.4 GB of VRAM at 8k context.
Does this model support image inputs?
No, CodeGemma 1.1 7b is a text‑only model.
What is the maximum context length?
The model supports up to 8192 tokens of context.