GLM-ASR-Nano-2512 needs about 2.0 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 28 quants, from 0.0 GB to 3.2 GB (BF16).
GLM-ASR-Nano-2512: 1.59B parameter LLaMA model with 8192 context
GLM-ASR-Nano-2512 is a 1.59B parameter LLaMA-based model trained on 8192 context tokens. It is released under the MIT license and is available in multiple GGUF quantizations. The model is designed for lightweight local inference.
Good at
- 1.59B parameters in a compact format
- 8192 token context
- MIT licensed for free use
Limits
- No vision support
- No mixture of experts
- Requires llama.cpp for inference
Best for
- Edge inference on low‑memory devices
- Rapid prototyping of LLM applications
- Local deployment without cloud access
Who it’s for. Developers and researchers who need a small, open‑source LLaMA model for local deployment. The model is suitable for environments with limited GPU memory and no need for vision capabilities.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.0 GB | Fits | Get file → | |
| IQ1_S | 0.5 GB | 1.5 GB | Fits | Get file → | |
| IQ1_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ2_XXS | 0.6 GB | 1.5 GB | Fits | Get file → | |
| IQ2_XS | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ2_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q2_K_S | 0.6 GB | 1.6 GB | Fits | Get file → | |
| IQ2_M | 0.6 GB | 1.6 GB | Fits | Get file → | |
| Q2_K_M | 0.7 GB | 1.6 GB | Fits | Get file → | |
| IQ3_XXS | 0.7 GB | 1.7 GB | Fits | Get file → | |
| IQ3_XS | 0.8 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_S | 0.8 GB | 1.8 GB | Fits | Get file → | |
| IQ3_M | 0.8 GB | 1.8 GB | Fits | Get file → | |
| Q3_K_M | 0.8 GB | 1.8 GB | Fits | Get file → | |
| IQ4_NL | 0.9 GB | 1.9 GB | Fits | Get file → | |
| IQ4_XS | 0.9 GB | 1.9 GB | Fits | Get file → | |
| Q4_K_S | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q4_1 | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q4_0 | 1.0 GB | 2.0 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q5_0 | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_M | 1.2 GB | 2.2 GB | Fits | Get file → | |
| Q5_1 | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q6_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q8_0 | 1.7 GB | 2.7 GB | Fits | Get file → | |
| BF16 | 2.4 GB | 3.4 GB | Fits | Get file → | |
| F16 | 2.4 GB | 3.4 GB | Fits | Get file → | |
| BF16 | 3.2 GB | 4.2 GB | Fits | Get file → |
For 4‑8 GB VRAM, use Q4_K_M (1.06 GB file, ~2 GB VRAM at 8k context). For 8‑12 GB VRAM, Q5_K_M (1.22 GB file, ~2.2 GB VRAM) or Q8_0 (1.7 GB file, ~2.7 GB VRAM) provide higher precision. File sizes and memory estimates are approximate.
What GPU do you need for GLM-ASR-Nano-2512?
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 BF16 (2.4 GB file, about 3.4 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (3.2 GB file, about 4.2 GB in use).
Which GLM-ASR-Nano-2512 quant should you choose?
Q4_K_M is the usual starting point for GLM-ASR-Nano-2512: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.7 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about GLM-ASR-Nano-2512
How much VRAM does GLM-ASR-Nano-2512 need?
About 2.0 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 GLM-ASR-Nano-2512 on an 8 GB GPU?
Yes, with BF16: the 3.2 GB file needs about 4.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of GLM-ASR-Nano-2512 GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.5 GB, IQ1_M is 0.6 GB, IQ2_XXS is 0.6 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB and 22 more.
What context length does GLM-ASR-Nano-2512 support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.
Where can I download GLM-ASR-Nano-2512 GGUF?
The files are on Hugging Face in the Mungert/GLM-ASR-Nano-2512-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 GLM-ASR-Nano-2512 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 GLM-ASR-Nano-2512 on 4 GB VRAM?
Yes, using the Q4_K_M quantization requires about 2 GB VRAM at 8k context.
Does GLM-ASR-Nano-2512 support vision?
No, the model does not include vision capabilities.