Scal-lite-60b-code-math needs about 56.6 GB of memory at Q4_K_M (a 55.5 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 24 quants, from 0.1 GB to 78.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
Scal-lite-60b-code-math: a 73.8B parameter MoE model pruned for code and math
Scal-lite-60b-code-math is a 73.8‑billion‑parameter model derived from gpt‑oss‑120b. It uses Activation‑Guided Structural Pruning to reduce experts from 128 to 64, preserving specialized skills in Spanish, LaTeX, and strict JSON/Python code generation. The model is released under Apache‑2.0.
Good at
- Advanced code generation
- Mathematical reasoning
- Spanish language support
Limits
- Large VRAM requirement (~120 GB BF16)
- No vision support
- Requires 131072‑token context
Best for
- Solving algorithmic programming problems
- Generating LaTeX‑formatted math
- Producing strict JSON/Python code
Who it’s for. Developers and researchers needing a high‑capacity MoE model for code and math tasks on powerful GPUs. The model is suitable for environments that can accommodate its large VRAM footprint and support for 131072‑token context.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.2 GB | Fits | Get file → | |
| IQ1_M | 41.8 GB | 42.9 GB | Too big | Get file → | |
| IQ1_S | 41.8 GB | 42.9 GB | Too big | Get file → | |
| IQ2_XXS | 41.8 GB | 42.9 GB | Too big | Get file → | |
| IQ2_XS | 41.8 GB | 42.9 GB | Too big | Get file → | |
| Q3_K_S | 41.9 GB | 43.0 GB | Too big | Get file → | |
| IQ2_M | 41.9 GB | 43.0 GB | Too big | Get file → | |
| IQ2_S | 41.9 GB | 43.0 GB | Too big | Get file → | |
| IQ3_S | 41.9 GB | 43.0 GB | Too big | Get file → | |
| IQ3_XS | 41.9 GB | 43.0 GB | Too big | Get file → | |
| IQ3_XXS | 41.9 GB | 43.0 GB | Too big | Get file → | |
| Q2_K | 41.9 GB | 43.0 GB | Too big | Get file → | |
| IQ4_XS | 41.9 GB | 43.0 GB | Too big | Get file → | |
| Q4_0 | 42.1 GB | 43.2 GB | Too big | Get file → | |
| Q2_K_S | 42.2 GB | 43.3 GB | Too big | Get file → | |
| IQ3_M | 42.3 GB | 43.4 GB | Too big | Get file → | |
| Q3_K_M | 45.0 GB | 46.1 GB | Too big | Get file → | |
| Q3_K_L | 46.5 GB | 47.6 GB | Too big | Get file → | |
| Q4_1 | 46.5 GB | 47.6 GB | Too big | Get file → | |
| Q4_K_S | 51.2 GB | 52.3 GB | Too big | Get file → | |
| Q4_K_M | 55.5 GB | 56.6 GB | Too big | Get file → | |
| Q5_K_S | 55.6 GB | 56.7 GB | Too big | Get file → | |
| Q5_K_M | 59.4 GB | 60.5 GB | Too big | Get file → | |
| Q6_K | 78.4 GB | 79.5 GB | Too big | Get file → |
For 8‑GB VRAM use the 0.1‑GB unknown quant, which estimates 1.2‑GB memory at 8K context. For 16‑GB VRAM choose IQ1_M or IQ1_S (41.81 GB file, 42.9 GB memory). For 24‑GB VRAM pick IQ2_XXS or IQ2_XS (≈42 GB file, 43 GB memory). For 32‑GB VRAM use Q3_K_S (41.88 GB file, 43 GB memory).
What GPU do you need for Scal-lite-60b-code-math?
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 the main file (0.1 GB file, about 1.2 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.2 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.2 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.2 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.2 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.2 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q4_1 (46.5 GB file, about 47.6 GB in use).
Which Scal-lite-60b-code-math quant should you choose?
Q4_K_M is the usual starting point for Scal-lite-60b-code-math: it balances file size and quality well. Here it is a 55.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 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 Scal-lite-60b-code-math
How much VRAM does Scal-lite-60b-code-math need?
About 56.6 GB at Q4_K_M with an 8K context window. That is the 55.5 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 Scal-lite-60b-code-math on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Scal-lite-60b-code-math GGUF?
It depends on the quant: file is 0.1 GB, IQ1_M is 41.8 GB, IQ1_S is 41.8 GB, IQ2_XXS is 41.8 GB, IQ2_XS is 41.8 GB, Q3_K_S is 41.9 GB and 18 more.
What context length does Scal-lite-60b-code-math support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download Scal-lite-60b-code-math GGUF?
The files are on Hugging Face in the mradermacher/scal-lite-60b-code-math-i1-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 Scal-lite-60b-code-math 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?
Only the 0.1‑GB unknown quant can fit, estimating 1.2‑GB memory at 8K context, but performance will be limited.
Does the model support image input?
No, the model has no vision capability.
What context length does the model support?
It supports up to 131072 tokens, which is the trained context length.