LFM2 350M ENJP MT 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 7 quants, from 0.2 GB (Q4_0) to 1.4 GB (F32). Longer context needs more: at 32K tokens the KV cache alone adds about 2.1 GB.
LFM2 350M ENJP MT – bi‑directional Japanese/English translation
LFM2 350M ENJP MT is a 0.354 billion‑parameter model fine‑tuned for near real‑time translation between Japanese and English. It supports short‑to‑medium inputs and delivers quality comparable to much larger models.
Good at
- Japanese ↔ English translation
- Short‑to‑medium text
- Technical and formal content
Limits
- No vision support
- Limited to 128 000 context tokens
- License is other
Best for
- Translation of product descriptions
- Technical documentation translation
- Business communication
Who it’s for. Developers and content creators needing efficient Japanese/English translation in local LLM setups. Suitable for projects with limited GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.2 GB | 1.3 GB | Fits | Get file → | |
| Q4_K_M | 0.2 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 → | |
| F32 | 1.4 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0 or Q4_K_M (0.22 GB or 0.23 GB). For 12 GB VRAM, Q5_K_M or Q6_K (0.26 GB or 0.29 GB) are suitable. Higher precision quants require more memory.
What GPU do you need for LFM2 350M ENJP MT?
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 F32 (1.4 GB file, about 2.5 GB in use).
Which LFM2 350M ENJP MT quant should you choose?
Q4_K_M is the usual starting point for LFM2 350M ENJP MT: 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 Q4_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2 350M ENJP MT
How much VRAM does LFM2 350M ENJP MT 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 LFM2 350M ENJP MT on an 8 GB GPU?
Yes, with F32: the 1.4 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 LFM2 350M ENJP MT GGUF?
It depends on the quant: Q4_0 is 0.2 GB, Q4_K_M is 0.2 GB, Q5_K_M is 0.3 GB, Q6_K is 0.3 GB, Q8_0 is 0.4 GB, F16 is 0.7 GB and 1 more.
What context length does LFM2 350M ENJP MT 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 LFM2 350M ENJP MT GGUF?
The files are on Hugging Face in the LiquidAI/LFM2-350M-ENJP-MT-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 LFM2 350M ENJP MT use?
Hugging Face lists the license as other. 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 LFM2 350M ENJP MT on 8 GB VRAM?
Yes, the Q4_0 or Q4_K_M quantized models fit within 8 GB VRAM with an estimated 1.3 GB usage at 8k context.
Does the model support image input?
No, the model has no vision capabilities.
What is the maximum context length?
The model was trained with 128 000 context tokens.