kAI Bolt 0.8B needs about 1.5 GB of memory at Q4_K_M (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.6 GB (Q4_K_M) to 1.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
kAI Bolt 0.8B – fast decision‑making model
kAI Bolt 0.8B is a QLoRA fine‑tune of Qwen3.5‑0.8B. It returns probabilities for options instead of generating text. The model supports a 262,144‑token context window and is released as GGUF.
Good at
- Fast probability scoring
- Long‑context decision tasks
- Low‑latency inference
Limits
- No chat or text generation
- No vision support in this variant
- Requires a 262,144‑token context window
Best for
- Triage and routing systems
- Intent classification
- Decision‑making pipelines
Who it’s for. Developers who need a lightweight, high‑speed model to evaluate options quickly. The model is ideal for prototyping and research where probability outputs are required rather than full responses.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q8_0 | 0.9 GB | 1.8 GB | Fits | Get file → | |
| F16 | 1.6 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.58 GB, ~1.5 GB memory at 8 k context) or Q6_K (0.68 GB, ~1.6 GB). For 12 GB VRAM, Q8_0 (0.87 GB, ~1.8 GB) or F16 (1.57 GB, ~2.5 GB) are suitable. Estimates are approximate.
What GPU do you need for kAI Bolt 0.8B?
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 F16 (1.6 GB file, about 2.5 GB in use).
Which kAI Bolt 0.8B quant should you choose?
Q4_K_M is the usual starting point for kAI Bolt 0.8B: it balances file size and quality well. Here it is a 0.6 GB file.
The Q8_0 file is 0.9 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 kAI Bolt 0.8B
How much VRAM does kAI Bolt 0.8B need?
About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.6 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 kAI Bolt 0.8B on an 8 GB GPU?
Yes, with F16: the 1.6 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kAI Bolt 0.8B GGUF?
It depends on the quant: Q4_K_M is 0.6 GB, Q6_K is 0.7 GB, Q8_0 is 0.9 GB, F16 is 1.6 GB.
What context length does kAI Bolt 0.8B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download kAI Bolt 0.8B GGUF?
The files are on Hugging Face in the Franci11/kAI_Bolt_0.8B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does kAI Bolt 0.8B 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 kAI Bolt 0.8B on 8 GB VRAM?
Yes, the Q4_K_M or Q6_K quantizations fit within 8 GB VRAM with about 1.5–1.6 GB memory usage at 8 k context.
Does kAI Bolt 0.8B support vision?
No, this variant does not provide vision capabilities despite the parent model's multimodal training.
Is kAI Bolt 0.8B suitable for chat applications?
No, it is designed to return probabilities for options, not to generate chat transcripts.