MiniCPM-S-1B-sft-llama-format needs about 2.3 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.6 GB (Q2_K) to 2.9 GB (F16).
MiniCPM‑S‑1B‑sft‑llama‑format: 1.47B LLaMA model with activation sparsity
MiniCPM‑S‑1B‑sft‑llama‑format is a 1.47B‑parameter LLaMA model fine‑tuned with ProSparse activation sparsity. It supports a 4096‑token context window and is released under the apache‑2.0 license. The model is available in multiple GGUF quantizations.
Good at
- High activation sparsity for faster inference
- Compatible with llama.cpp
- Supports 4096‑token context
Limits
- No vision support
- Requires bos token at start
- License is apache‑2.0
Best for
- Chat applications
- Lightweight inference on edge devices
- Rapid prototyping with llama.cpp
Who it’s for. Developers and researchers needing a compact LLaMA model with sparse activations for efficient inference. The model is suitable for local deployment and experimentation with different quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ3_XS | 0.7 GB | 1.6 GB | Fits | Get file → | |
| IQ3_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| IQ3_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 0.7 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_L | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ4_XS | 0.8 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q5_K_S | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q6_K | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q8_0 | 1.6 GB | 2.5 GB | Fits | Get file → | |
| F16 | 2.9 GB | 3.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.9 GB file, ~2.3 GB VRAM) or Q5_K_S (1.03 GB file, ~2.4 GB VRAM). If 12 GB VRAM is available, Q6_K (1.21 GB file, ~2.6 GB VRAM) or Q8_0 (1.57 GB file, ~2.9 GB VRAM) provide higher precision. Memory estimates are approximate.
What GPU do you need for MiniCPM-S-1B-sft-llama-format?
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 (1.6 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (2.9 GB file, about 4.3 GB in use).
Which MiniCPM-S-1B-sft-llama-format quant should you choose?
Q4_K_M is the usual starting point for MiniCPM-S-1B-sft-llama-format: it balances file size and quality well. Here it is a 0.9 GB file.
The Q8_0 file is 1.6 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 0.6 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 MiniCPM-S-1B-sft-llama-format
How much VRAM does MiniCPM-S-1B-sft-llama-format need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 0.9 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 MiniCPM-S-1B-sft-llama-format on an 8 GB GPU?
Yes, with F16: the 2.9 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM-S-1B-sft-llama-format GGUF?
It depends on the quant: Q2_K is 0.6 GB, IQ3_XS is 0.7 GB, IQ3_S is 0.7 GB, Q3_K_S is 0.7 GB, IQ3_M is 0.7 GB, Q3_K_M is 0.7 GB and 9 more.
What context length does MiniCPM-S-1B-sft-llama-format support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.4 GB at 4K.
Where can I download MiniCPM-S-1B-sft-llama-format GGUF?
The files are on Hugging Face in the mradermacher/MiniCPM-S-1B-sft-llama-format-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 MiniCPM-S-1B-sft-llama-format 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 this model on 8 GB VRAM?
Yes, quantizations such as Q4_K_M or Q5_K_S fit within 8 GB VRAM, using roughly 2.3–2.4 GB of memory at 8k context.
Does the model support vision tasks?
No, the model does not include vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.