ibm granite granite 20b code instruct needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB (Q4_1) to 8.7 GB (IQ3_XS).
Granite 20B Code Instruct – a 1.9B parameter model for coding tasks
Granite 20B Code Instruct is a 1.9 B parameter model focused on code generation. It was quantized by RichardErkhov and is available in multiple GGUF quantizations. The model supports a variety of programming languages and is optimized for text‑generation pipelines.
Good at
- Code generation in Python, JavaScript, Java, Go, C++, Rust
- Large context handling up to 8 k tokens
- Instruction‑following for coding tasks
Limits
- No vision support
- License not specified
- Requires at least 0.5 GB VRAM for Q4_1 at 8 k context
Best for
- Writing code snippets
- Automating code reviews
- Generating coding documentation
Who it’s for. Developers and researchers needing a lightweight code generation model. The model is suitable for local inference with llama.cpp and can be run on modest GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q6_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_NL | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_L | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q3_K_S | 0.6 GB | 1.2 GB | Fits | Get file → | |
| IQ3_S | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q2_K | 7.9 GB | 9.4 GB | Too big | Get file → | |
| IQ3_XS | 8.7 GB | 10.2 GB | Too big | Get file → |
For 8 GB VRAM, Q4_1, Q4_K_M, Q5_0, Q5_1, Q5_K, Q5_K_M, Q5_K_S, Q6_K, Q8_0, IQ4_NL, IQ4_XS, Q4_0, Q4_K, Q4_K_S, Q3_K, IQ3_M, Q3_K_S, IQ3_S, Q2_K, IQ3_XS are available. The smallest file is Q3_K (0.04 GB) but needs 9.4 GB VRAM. For 8 GB VRAM, use Q4_1 or Q4_K_M (0.5 GB memory).
What GPU do you need for ibm granite granite 20b code instruct?
These figures add the file size, an fp16 KV cache at an 8K context window 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 IQ3_S (0.9 GB file, about 1.5 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_S (0.9 GB file, about 1.5 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_S (0.9 GB file, about 1.5 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_XS (8.7 GB file, about 10.2 GB in use).
Which ibm granite granite 20b code instruct quant should you choose?
Q4_K_M is the usual starting point for ibm granite granite 20b code instruct: it balances file size and quality well. Here it is a 0.0 GB file.
The Q8_0 file is 0.0 GB, about NaN 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 Q4_1 at 0.0 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about ibm granite granite 20b code instruct
How much VRAM does ibm granite granite 20b code instruct need?
About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 ibm granite granite 20b code instruct on an 8 GB GPU?
Yes, with IQ3_S: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ibm granite granite 20b code instruct GGUF?
It depends on the quant: Q4_1 is 0.0 GB, Q4_K_M is 0.0 GB, Q5_0 is 0.0 GB, Q5_1 is 0.0 GB, Q5_K is 0.0 GB, Q5_K_M is 0.0 GB and 16 more.
Where can I download ibm granite granite 20b code instruct GGUF?
The files are on Hugging Face in the RichardErkhov/ibm-granite_-_granite-20b-code-instruct-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 this model on 8 GB VRAM?
Yes, using Q4_1 or Q4_K_M quantizations, which require about 0.5 GB VRAM at 8 k context.
Does the model support image inputs?
No, the model has no vision capabilities.
What is the approximate VRAM needed for Q3_K_S?
Q3_K_S needs about 1.2 GB VRAM at 8 k context.