Polyglot Lion 1.7b v1.5 needs about 2.5 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.8 GB (Q2_K) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
Polyglot Lion 1.7b v1.5 – multilingual ASR with vision support
Polyglot Lion 1.7b v1.5 is a 1.72B parameter model fine‑tuned on Singapore’s four official languages. It supports audio and vision inputs and runs in GGUF format via llama.cpp. The model was trained on public speech corpora without punctuation removal.
Good at
- Multilingual speech recognition
- Vision‑enabled inference
- Compact GGUF quantizations
Limits
- No language‑tag conditioning
- No explicit vision model training
- Requires 8k context for memory estimates
Best for
- Speech‑to‑text on Singapore languages
- Multimodal inference with image prompts
- Low‑latency inference on mid‑range GPUs
Who it’s for. Developers building multilingual ASR services for Singapore. Researchers needing a lightweight, vision‑capable model for prototyping. Hobbyists wanting to run speech recognition on consumer GPUs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 2.2 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 2.3 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 2.4 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 2.4 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| Q5_K_S | 1.2 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 1.4 GB | 2.9 GB | Fits | Get file → | |
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (file size 1.11 GB, estimated 2.5 GB memory). For 4 GB VRAM use Q3_K_S (file size 0.87 GB, estimated 2.3 GB memory). For 2 GB VRAM use Q2_K (file size 0.78 GB, estimated 2.2 GB memory).
What GPU do you need for Polyglot Lion 1.7b v1.5?
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 Q8_0 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).
Which Polyglot Lion 1.7b v1.5 quant should you choose?
Q4_K_M is the usual starting point for Polyglot Lion 1.7b v1.5: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.8 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 0.8 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 Polyglot Lion 1.7b v1.5
How much VRAM does Polyglot Lion 1.7b v1.5 need?
About 2.5 GB at Q4_K_M with an 8K context window. That is the 1.1 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 Polyglot Lion 1.7b v1.5 on an 8 GB GPU?
Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Polyglot Lion 1.7b v1.5 GGUF?
It depends on the quant: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, Q4_K_S is 1.1 GB and 6 more.
What context length does Polyglot Lion 1.7b v1.5 support?
The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download Polyglot Lion 1.7b v1.5 GGUF?
The files are on Hugging Face in the mradermacher/polyglot-lion-1.7b-v1.5-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 Polyglot Lion 1.7b v1.5 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 Polyglot Lion 1.7b v1.5 on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.5 GB memory at 8k context, leaving room for other processes.
Does the model support vision inputs?
Yes, the model has detected vision abilities and can process image data alongside audio.
What license does the model use?
The model is released under the MIT license.