JackOD 9B Coder needs about 7.4 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 28 quants, from 3.4 GB (IQ2_XS) to 18.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
JackOD 9B Coder – a 9‑billion‑parameter text‑only model for multi‑turn coding tasks
JackOD 9B Coder is a 9‑billion‑parameter model built on a four‑way omnimerge of Qwen3.5‑9B, Coder‑Flash, Ornith‑1.5‑9B and DeltaCoder. It is designed for multi‑turn agentic coding, staying on a task across turns and tool calls until completion. The model is text‑only, with no vision tower.
Good at
- Multi‑turn coding with tool calls
- Agentic task completion
- Code generation in a conversational context
Limits
- No vision support
- Large context size requires high VRAM
- Apache‑2.0 license limits commercial use
Best for
- Developers building coding assistants
- Researchers testing agentic coding workflows
- Teams needing a text‑only coding model
Who it’s for. Developers and researchers who need a dedicated coding model that can maintain context over multiple turns and tool calls. The model is suitable for building coding assistants or testing agentic coding workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 3.4 GB | 5.0 GB | Fits | Get file → | |
| IQ2_S | 3.6 GB | 5.2 GB | Fits | Get file → | |
| IQ2_M | 3.7 GB | 5.4 GB | Fits | Get file → | |
| Q2_K | 3.9 GB | 5.6 GB | Fits | Get file → | |
| IQ3_XXS | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q3_K_S | 4.4 GB | 6.0 GB | Fits | Get file → | |
| IQ3_XS | 4.4 GB | 6.0 GB | Fits | Get file → | |
| IQ3_M | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q3_K_M | 4.7 GB | 6.3 GB | Fits | Get file → | |
| Q2_K_L | 4.9 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_L | 5.0 GB | 6.6 GB | Fits | Get file → | |
| Q3_K_L | 5.0 GB | 6.7 GB | Fits | Get file → | |
| IQ4_XS | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_S | 5.5 GB | 7.1 GB | Fits | Get file → | |
| IQ4_NL | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q3_K_XL | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q4_K_M | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_M | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_S | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_L | 6.5 GB | 8.1 GB | Too big | Get file → | |
| Q5_K_M | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q5_K_M | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q5_K_L | 7.3 GB | 8.9 GB | Too big | Get file → | |
| Q6_K | 7.5 GB | 9.1 GB | Too big | Get file → | |
| Q6_K | 7.6 GB | 9.2 GB | Too big | Get file → | |
| Q6_K_L | 8.1 GB | 9.7 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 11.4 GB | Too big | Get file → | |
| F16 | 18.4 GB | 20.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_S or Q2_K (≈5 GB file, 5.2–5.6 GB VRAM at 8 k context). For 12 GB VRAM, Q4_K_S or IQ4_XS (≈5.5–5.3 GB file, 7.1–6.9 GB VRAM). For 24 GB VRAM, Q6_K or Q6_K_L (≈7.5–8.0 GB file, 9.1–9.7 GB VRAM). Memory estimates are approximate.
What GPU do you need for JackOD 9B 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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is IQ3_XS (4.4 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (5.8 GB file, about 7.4 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (18.4 GB file, about 20.0 GB in use).
Which JackOD 9B Coder quant should you choose?
Q4_K_M is the usual starting point for JackOD 9B Coder: it balances file size and quality well. Here it is a 5.8 GB file.
The Q8_0 file is 9.8 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 IQ2_XS 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 JackOD 9B Coder
How much VRAM does JackOD 9B Coder need?
About 7.4 GB at Q4_K_M with an 8K context window. That is the 5.8 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 JackOD 9B Coder on an 8 GB GPU?
Yes, with Q4_K_M: 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 JackOD 9B Coder GGUF?
It depends on the quant: IQ2_XS is 3.4 GB, IQ2_S is 3.6 GB, IQ2_M is 3.7 GB, Q2_K is 3.9 GB, IQ3_XXS is 4.1 GB, Q3_K_S is 4.4 GB and 22 more.
What context length does JackOD 9B 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 4.4 GB at 32K.
Where can I download JackOD 9B Coder GGUF?
The files are on Hugging Face in the ManniX-ITA/JackOD-9B-Coder-MTP-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 JackOD 9B Coder use?
Hugging Face lists the license as apache-2.0. 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 JackOD 9B Coder on 8 GB VRAM?
Yes, with a low‑precision quant like IQ2_S or Q2_K, which use about 5–5.6 GB of VRAM at 8 k context.
Does this model support image input?
No, JackOD 9B Coder is text‑only and has no vision tower or mmproj weights.
What license applies to this model?
The model is released under the Apache‑2.0 license, which allows commercial use with attribution.