Shark-Coder-9b needs about 7.3 GB of memory at Q4_K_M (a 5.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 3.4 GB (Q2_K) to 18.0 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Shark-Coder-9b – 8.99B llama model focused on coding
Shark-Coder-9b is an 8.99B parameter llama model optimized for code generation. It was created by merging Shark-1 and The-Trinity-Coder-7B. The model supports a 32,768 token context window.
Good at
- Code generation
- Language syntax understanding
- Programming assistance
Limits
- No vision support
- License not specified
- Large VRAM requirement for higher quants
Best for
- Writing scripts
- Debugging code snippets
- Learning programming concepts
Who it’s for. Developers and programmers seeking a dedicated coding assistant. The model is suitable for those who need a large context window for complex codebases.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.4 GB | 5.2 GB | Fits | Get file → | |
| IQ3_XS | 3.7 GB | 5.6 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.8 GB | Fits | Get file → | |
| IQ3_S | 3.9 GB | 5.8 GB | Fits | Get file → | |
| IQ3_M | 4.1 GB | 5.9 GB | Fits | Get file → | |
| Q3_K_M | 4.4 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.7 GB | 6.6 GB | Fits | Get file → | |
| IQ4_XS | 4.9 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_S | 5.1 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.4 GB | 7.3 GB | Tight | Get file → | |
| Q5_K_S | 6.2 GB | 8.0 GB | Too big | Get file → | |
| Q5_K_M | 6.4 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 7.4 GB | 9.2 GB | Too big | Get file → | |
| Q8_0 | 9.6 GB | 11.4 GB | Too big | Get file → | |
| F16 | 18.0 GB | 19.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 5.42 GB, estimated 7.3 GB memory). For 12 GB VRAM, Q5_K_M (6.36 GB, 8.2 GB memory) is a good balance. If you have 16 GB VRAM, consider Q6_K (7.37 GB, 9.2 GB memory).
What GPU do you need for Shark-Coder-9b?
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: the best quant that fits is IQ3_M (4.1 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_S (6.2 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.6 GB file, about 11.4 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (18.0 GB file, about 19.8 GB in use).
Which Shark-Coder-9b quant should you choose?
Q4_K_M is the usual starting point for Shark-Coder-9b: it balances file size and quality well. Here it is a 5.4 GB file.
The Q8_0 file is 9.6 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 3.4 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 Shark-Coder-9b
How much VRAM does Shark-Coder-9b need?
About 7.3 GB at Q4_K_M with an 8K context window. That is the 5.4 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 Shark-Coder-9b on an 8 GB GPU?
Yes, with Q5_K_S: the 6.2 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 Shark-Coder-9b GGUF?
It depends on the quant: Q2_K is 3.4 GB, IQ3_XS is 3.7 GB, Q3_K_S is 3.9 GB, IQ3_S is 3.9 GB, IQ3_M is 4.1 GB, Q3_K_M is 4.4 GB and 9 more.
What context length does Shark-Coder-9b support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Shark-Coder-9b GGUF?
The files are on Hugging Face in the mradermacher/Shark-Coder-9b-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 Q4_K_M on 8 GB VRAM?
Yes, Q4_K_M requires about 7.3 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does Shark-Coder-9b support image inputs?
No, the model does not have vision capabilities.
What is the maximum context length?
The model was trained with a 32,768 token context window.