Imagine v10 needs about 3.0 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.8 GB (Q4_0) to 2.7 GB (F16).
Compact local coding model focused on PostgreSQL and analytical SQL
Imagine v10 is a 1.35B parameter llama model fine‑tuned for PostgreSQL generation and complex analytical queries. It runs locally via llama.cpp and requires no GPU or API key. The model is licensed under apache-2.0.
Good at
- Complex analytical SQL generation
- Schema‑grounded text‑to‑SQL
- Local‑first inference
Limits
- No vision support
- Requires 8‑k context for estimates
- No GPU needed but large VRAM for higher quants
Best for
- PostgreSQL query generation
- Database reasoning tasks
- Local coding assistance
Who it’s for. Developers and data engineers who need accurate, schema‑grounded SQL from natural language prompts. Ideal for self‑hosted environments where privacy and control are priorities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.8 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 0.9 GB | 3.0 GB | Fits | Get file → | |
| Q5_K_M | 1.0 GB | 3.1 GB | Fits | Get file → | |
| Q8_0 | 1.4 GB | 3.5 GB | Fits | Get file → | |
| F16 | 2.7 GB | 4.8 GB | Fits | Get file → |
For 8‑GB VRAM, use Q4_0 (0.78 GB, ~2.9 GB memory) or Q4_K_M (0.87 GB, ~3 GB). If 12‑GB VRAM is available, Q5_K_M (1 GB, ~3.1 GB) or Q8_0 (1.43 GB, ~3.5 GB) provide higher precision. F16 (2.69 GB, ~4.8 GB) is suitable for 16‑GB VRAM setups.
What GPU do you need for Imagine v10?
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 Q8_0 (1.4 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (2.7 GB file, about 4.8 GB in use).
Which Imagine v10 quant should you choose?
Q4_K_M is the usual starting point for Imagine v10: it balances file size and quality well. Here it is a 0.9 GB file.
The Q8_0 file is 1.4 GB, about 1.6 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_0 at 0.8 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
Source
Frequently asked questions about Imagine v10
How much VRAM does Imagine v10 need?
About 3.0 GB at Q4_K_M with an 8K context window. That is the 0.9 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 Imagine v10 on an 8 GB GPU?
Yes, with F16: the 2.7 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Imagine v10 GGUF?
It depends on the quant: Q4_0 is 0.8 GB, Q4_K_M is 0.9 GB, Q5_K_M is 1.0 GB, Q8_0 is 1.4 GB, F16 is 2.7 GB.
What context length does Imagine v10 support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.
Where can I download Imagine v10 GGUF?
The files are on Hugging Face in the Interchained/imagine-v10 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Imagine v10 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 Imagine v10 on 8 GB VRAM?
Yes, with Q4_0 or Q4_K_M quantizations, which use about 2.9–3 GB of VRAM at 8‑k context.
Does Imagine v10 support image input?
No, the model has no vision capability and only processes text.