ajibawa-2023_code-33b needs about 33.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 12 quants, from 13.5 GB (Q2_K) to 34.6 GB (Q8_0).
32.5B‑parameter Code‑33B model for code generation
The model is a 32.5B‑parameter Llama‑based LLM fine‑tuned on code and explanations. It was trained on 74000 code sets across multiple languages and 3 epochs on 4×A100 GPUs. The GGUF quantized versions are available for local inference.
Good at
- Code generation with explanations
- Multi‑language coding support
- Fine‑tuned for programming tasks
Limits
- No vision support
- License cc‑by‑nc‑nd‑4.0
- Requires GPU for efficient inference
Best for
- Developers needing code snippets
- Educational coding assistants
- Automated code documentation
Who it’s for. Engineers, students, and hobbyists who want a local LLM that can produce and explain code. The model is ideal for environments where privacy or offline operation is required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 13.5 GB | 17.3 GB | Too big | Get file → | |
| Q3_K_S | 14.1 GB | 17.8 GB | Too big | Get file → | |
| Q3_K_M | 15.8 GB | 19.5 GB | Too big | Get file → | |
| Q3_K_L | 17.3 GB | 21.1 GB | Too big | Get file → | |
| Q4_0 | 18.4 GB | 22.1 GB | Too big | Get file → | |
| Q4_K_S | 18.4 GB | 22.2 GB | Too big | Get file → | |
| Q4_K_M | 19.6 GB | 23.4 GB | Too big | Get file → | |
| Q5_0 | 22.4 GB | 26.2 GB | Too big | Get file → | |
| Q5_K_S | 22.4 GB | 26.2 GB | Too big | Get file → | |
| Q5_K_M | 23.0 GB | 26.8 GB | Too big | Get file → | |
| Q6_K | 26.7 GB | 30.5 GB | Too big | Get file → | |
| Q8_0 | 34.6 GB | 38.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (18.36 GB file, ~31.9 GB memory). For 12 GB VRAM, Q4_K_M (19.62 GB file, ~33.2 GB memory) is suitable. If you have 16 GB VRAM, Q5_K_M (23.05 GB file, ~36.6 GB memory) offers higher quality. Estimates are approximate.
What GPU do you need for ajibawa-2023_code-33b?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q4_K_S (18.4 GB file, about 32.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (26.7 GB file, about 40.3 GB in use).
Which ajibawa-2023_code-33b quant should you choose?
Q4_K_M is the usual starting point for ajibawa-2023_code-33b: it balances file size and quality well. Here it is a 19.6 GB file.
The Q8_0 file is 34.6 GB, about 1.8 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 Q2_K at 13.5 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 ajibawa-2023_code-33b
How much VRAM does ajibawa-2023_code-33b need?
About 33.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 ajibawa-2023_code-33b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ajibawa-2023_code-33b GGUF?
It depends on the quant: Q2_K is 13.5 GB, Q3_K_S is 14.1 GB, Q3_K_M is 15.8 GB, Q3_K_L is 17.3 GB, Q4_0 is 18.4 GB, Q4_K_S is 18.4 GB and 6 more.
What context length does ajibawa-2023_code-33b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 13.1 GB at 8K and 3.3 GB at 2K.
Where can I download ajibawa-2023_code-33b GGUF?
The files are on Hugging Face in the TheBloke/Code-33B-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 ajibawa-2023_code-33b use?
Hugging Face lists the license as cc-by-nc-nd-4.0. 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 Q4_0 quantized file; it requires about 31.9 GB of VRAM at 8k context, so 8 GB is insufficient.
Does the model support image inputs?
No, the model has no vision capability.
What license applies to the model?
The model is licensed under cc‑by‑nc‑nd‑4.0.