Swift-1.5-Ornith-9B 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 5 quants, from 5.8 GB (Q4_K_M) to 18.4 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.
Swift-1.5-Ornith-9B: a 9.2B Qwen3.5 model with efficient reasoning and vision support
Swift-1.5-Ornith-9B is a 9.2B parameter Qwen3.5 model optimized for reasoning and tool use. It supports vision and runs on llama.cpp-compatible runtimes. The model is licensed under Apache‑2.0.
Good at
- Reasoning with fewer tokens
- Tool use and instruction following
- Vision input handling
Limits
- No vision support in all quantizations
- Large VRAM needed for higher quant levels
- Requires llama.cpp-compatible runtime
Best for
- Chatbots needing concise reasoning
- Tool‑enabled assistants
- Vision‑aware applications
Who it’s for. Developers building LLM‑powered assistants that require efficient reasoning and tool integration. The model is suitable for projects that can run llama.cpp or llama‑server and need a balance between performance and memory usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.8 GB | 7.4 GB | Tight | Get file → | |
| Q5_K_M | 6.6 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 7.6 GB | 9.2 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 11.4 GB | Too big | Get file → | |
| BF16 | 18.4 GB | 20.0 GB | Too big | Get file → |
For 8 GB VRAM, Q4_K_M (5.78 GB) or Q5_K_M (6.64 GB) are suitable, with estimated memory usage of 7.4 GB and 8.2 GB respectively. If 12 GB VRAM is available, Q6_K (7.56 GB) can be used, estimating 9.2 GB memory. The BF16 quant requires 18.41 GB and 20 GB memory, suitable only for high‑end GPUs.
What GPU do you need for Swift-1.5-Ornith-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: no quant fits at an 8K context.
- 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 BF16 (18.4 GB file, about 20.0 GB in use).
Which Swift-1.5-Ornith-9B quant should you choose?
Q4_K_M is the usual starting point for Swift-1.5-Ornith-9B: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Swift-1.5-Ornith-9B
How much VRAM does Swift-1.5-Ornith-9B 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 Swift-1.5-Ornith-9B 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 Swift-1.5-Ornith-9B GGUF?
It depends on the quant: Q4_K_M is 5.8 GB, Q5_K_M is 6.6 GB, Q6_K is 7.6 GB, Q8_0 is 9.8 GB, BF16 is 18.4 GB.
What context length does Swift-1.5-Ornith-9B 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 Swift-1.5-Ornith-9B GGUF?
The files are on Hugging Face in the ukisai/Swift-1.5-Ornith-9B-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 Swift-1.5-Ornith-9B 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 Swift‑1.5‑Ornith‑9B on 8 GB VRAM?
Yes, the Q4_K_M quantization is 5.78 GB and estimates 7.4 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support vision?
Yes, the model has detected vision ability, but all quantizations require a compatible runtime that supports image input.
What license does the model use?
The model is released under the Apache‑2.0 license, allowing free use and modification.