VELUM Coder needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 24 quants, from 0.0 GB to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
VELUM Coder – a 9‑B Qwen 3.5 based model for coding and vision
VELUM Coder is a 8.95‑B parameter model derived from Ornith‑1.5‑9B. It supports coding and vision tasks and is released under the MIT license. The model is available in multiple GGUF quantizations for local deployment.
Good at
- Code generation
- Debugging and refactoring
- Vision‑based code analysis
Limits
- No standard chat support
- Requires 262144 context tokens
- Large VRAM for high‑quality quantizations
Best for
- Local IDE assistants
- Automated code review tools
- Vision‑enabled code editors
Who it’s for. Developers and teams that need a local, code‑focused LLM with vision capabilities. The model runs on single‑GPU setups and can be integrated into agentic platforms or code editors.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ2_XXS | 3.1 GB | 4.7 GB | Fits | Get file → | |
| TQ2_0 | 3.2 GB | 4.8 GB | Fits | Get file → | |
| IQ2_XS | 3.3 GB | 4.9 GB | Fits | Get file → | |
| Q2_0 | 3.4 GB | 4.9 GB | Fits | Get file → | |
| IQ2_S | 3.4 GB | 5.0 GB | Fits | Get file → | |
| IQ2_M | 3.6 GB | 5.2 GB | Fits | Get file → | |
| Q2_K_S | 3.7 GB | 5.3 GB | Fits | Get file → | |
| Q2_K | 3.8 GB | 5.4 GB | Fits | Get file → | |
| IQ3_XXS | 3.9 GB | 5.5 GB | Fits | Get file → | |
| IQ1_M | 4.0 GB | 5.6 GB | Fits | Get file → | |
| IQ3_XS | 4.2 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 5.8 GB | Fits | Get file → | |
| IQ3_S | 4.4 GB | 5.9 GB | Fits | Get file → | |
| IQ3_M | 4.4 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_M | 4.6 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_S | 5.4 GB | 6.9 GB | Fits | Get file → | |
| IQ4_NL | 5.4 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q4_1 | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XXS (3.1 GB, 4.7 GB memory) or TQ2_0 (3.21 GB, 4.8 GB memory). For 12 GB VRAM, Q4_K_M (5.63 GB, 7.2 GB memory) or Q4_0 (5.33 GB, 6.9 GB memory) offer a good balance. For maximum fidelity on 16 GB VRAM, Q8_0 (9.53 GB, 11.1 GB memory) is recommended.
What GPU do you need for VELUM Coder?
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: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_M (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_1 (5.8 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
Which VELUM Coder quant should you choose?
Q4_K_M is the usual starting point for VELUM Coder: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VELUM Coder
How much VRAM does VELUM Coder need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 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 VELUM Coder on an 8 GB GPU?
Yes, with Q4_1: the 5.8 GB file needs about 7.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VELUM Coder GGUF?
It depends on the quant: file is 0.0 GB, IQ2_XXS is 3.1 GB, TQ2_0 is 3.2 GB, IQ2_XS is 3.3 GB, Q2_0 is 3.4 GB, IQ2_S is 3.4 GB and 18 more.
What context length does VELUM Coder support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download VELUM Coder GGUF?
The files are on Hugging Face in the guell00/VELUM-Coder repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does VELUM Coder use?
Hugging Face lists the license as mit. 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 VELUM Coder on 8 GB VRAM?
Yes, use a low‑bit quant like IQ2_XXS or TQ2_0, which fit within 8 GB VRAM and use about 4.7–4.8 GB memory at 8K context.
Does VELUM Coder support vision tasks?
Yes, the model has detected vision abilities and can process image inputs alongside text.
What license applies to VELUM Coder?
VELUM Coder is released under the MIT license, allowing free use and modification.