Bespoke-Nimble-9B-v3 needs about 7.9 GB of memory at Q4_K_M (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 6.3 GB (Q4_K_M) to 17.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Decision model based on Qwen3.5-9B with Bespoke LoRA
Bespoke-Nimble-9B-v3 is a LoRA adapter for Qwen/Qwen3.5-9B. It returns probabilities for typed questions such as multiple choice or yes/no. The model is trained on a 262,144 token context and is licensed under CC BY-NC 4.0.
Good at
- Multiple‑choice probability scoring
- Yes/No decision support
- Fast inference on 8‑k context
Limits
- Non‑commercial license only
- No vision or audio support
- Requires 8‑k context for full performance
Best for
- Decision‑making assistants
- Educational quiz generators
- Rapid prototyping of choice‑based models
Who it’s for. Developers building decision‑oriented applications who need a lightweight, non‑commercial model. Suitable for research and personal projects that require probability outputs for user queries.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → | |
| BF16 | 17.9 GB | 19.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (6.32 GB, ~7.9 GB memory). For 12 GB VRAM use Q8_0 (9.53 GB, ~11.1 GB memory). BF16 requires ~19.5 GB memory and is suitable only for high‑end GPUs.
What GPU do you need for Bespoke-Nimble-9B-v3?
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 (6.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (17.9 GB file, about 19.5 GB in use).
Which Bespoke-Nimble-9B-v3 quant should you choose?
Q4_K_M is the usual starting point for Bespoke-Nimble-9B-v3: it balances file size and quality well. Here it is a 6.3 GB file.
The Q8_0 file is 9.5 GB, about 1.5 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 Bespoke-Nimble-9B-v3
How much VRAM does Bespoke-Nimble-9B-v3 need?
About 7.9 GB at Q4_K_M with an 8K context window. That is the 6.3 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 Bespoke-Nimble-9B-v3 on an 8 GB GPU?
Yes, with Q4_K_M: the 6.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Bespoke-Nimble-9B-v3 GGUF?
It depends on the quant: Q4_K_M is 6.3 GB, Q8_0 is 9.5 GB, BF16 is 17.9 GB.
What context length does Bespoke-Nimble-9B-v3 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 Bespoke-Nimble-9B-v3 GGUF?
The files are on Hugging Face in the ggml-org/Bespoke-Nimble-9B-v3-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 Bespoke-Nimble-9B-v3 use?
Hugging Face lists the license as cc-by-nc-4.0. 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 Bespoke-Nimble-9B-v3 on 8 GB VRAM?
Yes, the Q4_K_M quantized file is 6.32 GB and uses about 7.9 GB of VRAM at 8‑k context.
Is this model suitable for commercial use?
No, the model is licensed under CC BY‑NC 4.0 and cannot be used commercially.
Does the model support image inputs?
No, Bespoke-Nimble-9B-v3 is a text‑only decision model with no vision capabilities.