Yoshino 0.8B needs about 1.5 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.4 GB (Q2_K) to 1.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Yoshino 0.8B – a distilled Qwen3.5 0.8B model for concise reasoning
Yoshino 0.8B is a fine‑tuned version of Qwen3.5 0.8B. It retains the base model size while improving reasoning clarity. The model is released under the MIT license and supports reasoning, tools, and vision.
Good at
- Reasoning
- Tool use
- Vision
Limits
- No vision support on all quant types
- Requires 8k context for memory estimates
- No agentic design
Best for
- General‑purpose chatbot
- Short‑form reasoning tasks
- Vision‑enabled prompts
Who it’s for. Developers building lightweight chatbots or agents that need reliable reasoning. The model is suitable for users who prefer a small footprint with decent reasoning and tool‑use capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.4 GB | 1.3 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.4 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.8 GB | Fits | Get file → | |
| F16 | 1.6 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (0.54 GB) or Q5_K_M (0.59 GB) are suitable, using about 1.5 GB of VRAM at 8k context. If memory is tighter, Q3_K_S (0.44 GB) or Q3_K_M (0.48 GB) use roughly 1.4 GB. For the highest quality, Q8_0 (0.83 GB) uses about 1.8 GB.
What GPU do you need for Yoshino 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 Yoshino 0.8B quant should you choose?
Q4_K_M is the usual starting point for Yoshino 0.8B: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 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.
If memory is tight, the smallest file is Q2_K at 0.4 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 Yoshino 0.8B
How much VRAM does Yoshino 0.8B need?
About 1.5 GB at Q4_K_M with an 8K context window. That is the 0.5 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 Yoshino 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 Yoshino 0.8B GGUF?
It depends on the quant: Q2_K is 0.4 GB, Q3_K_S is 0.4 GB, Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, IQ4_XS is 0.5 GB, Q4_K_S is 0.5 GB and 6 more.
What context length does Yoshino 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 1.7 GB at 32K.
Where can I download Yoshino 0.8B GGUF?
The files are on Hugging Face in the mradermacher/Yoshino-0.8B-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 Yoshino 0.8B use?
Hugging Face lists the license as mit. 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 Yoshino 0.8B on 8 GB VRAM?
Yes, quantized versions such as Q4_K_M or Q5_K_M fit within 8 GB VRAM, using about 1.5 GB at 8k context.
Does Yoshino 0.8B support vision?
Yes, the model has detected vision ability, but it is not guaranteed across all quant types.