shisa v2.1c lfm2 350m needs about 1.3 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.2 GB (Q2_K) to 0.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
Shisa v2.1c LFM2 350M – 0.354B parameter Japanese LLM
Shisa v2.1c LFM2 350M is a 0.354 billion parameter language model optimized for Japanese. It supports a 128 000 token context window and is available in multiple GGUF quantizations. The model was trained on an 8xMI300X node on the AMD Developer Cloud.
Good at
- Japanese language generation
- Long‑context handling
- Low‑memory inference
Limits
- No vision support
- License not specified
- No mixture of experts
Best for
- Chatbots needing Japanese support
- Content creation with long prompts
- Research prototyping
Who it’s for. Developers and researchers who need a Japanese LLM that can run on consumer GPUs with limited VRAM. The model is suitable for applications that require extended context and efficient inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 1.2 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 1.2 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 1.3 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.4 GB | Fits | Get file → | |
| F16 | 0.7 GB | 1.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_S (0.22 GB) or Q4_K_M (0.23 GB). For 4 GB VRAM, use Q3_K_S (0.18 GB) or Q3_K_M (0.19 GB). For 2 GB VRAM, use Q2_K (0.16 GB). Estimates are approximate.
What GPU do you need for shisa v2.1c lfm2 350m?
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 (0.7 GB file, about 1.7 GB in use).
Which shisa v2.1c lfm2 350m quant should you choose?
Q4_K_M is the usual starting point for shisa v2.1c lfm2 350m: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.4 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.
If memory is tight, the smallest file is Q2_K at 0.2 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 shisa v2.1c lfm2 350m
How much VRAM does shisa v2.1c lfm2 350m need?
About 1.3 GB at Q4_K_M with an 8K context window. That is the 0.2 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 shisa v2.1c lfm2 350m on an 8 GB GPU?
Yes, with F16: the 0.7 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of shisa v2.1c lfm2 350m GGUF?
It depends on the quant: Q2_K is 0.2 GB, Q3_K_S is 0.2 GB, Q3_K_M is 0.2 GB, Q3_K_L is 0.2 GB, IQ4_XS is 0.2 GB, Q4_K_S is 0.2 GB and 6 more.
What context length does shisa v2.1c lfm2 350m support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 2.1 GB at 32K.
Where can I download shisa v2.1c lfm2 350m GGUF?
The files are on Hugging Face in the mradermacher/shisa-v2.1c-lfm2-350m-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, using Q4_K_S or Q4_K_M quantizations which require about 1.3 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the model has no vision capabilities.
What is the context length of this model?
The model supports a 128 000 token context window.