VeriLoop E2 needs about 22.3 GB of memory at Q4_K_M (a 19.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 2.0 GB (Q5_K_M) to 53.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.
27B open-weight model for code, mathematics, and physics
VeriLoop E2 is a 27B post‑trained model built on Qwen3.8‑27B. It targets code, mathematics, and physics reasoning with a 262,144‑token native context window. The model is released under Apache‑2.0 and includes multiple GGUF quantizations.
Good at
- Code generation
- Mathematical reasoning
- Physics problem solving
Limits
- No vision support
- Requires 262,144‑token context for full capability
- Large memory footprint for higher‑quality quants
Best for
- Developers needing long‑context code assistance
- Researchers tackling math proofs
- Physics simulation scripting
Who it’s for. Engineers and scientists who need a large‑context model for complex code, math, or physics tasks. The model is open‑source and can be run locally with llama.cpp or served via vLLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 2.0 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 2.0 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 3.3 GB | 5.9 GB | Fits | Get file → | |
| BF16 | 6.0 GB | 8.7 GB | Too big | Get file → | |
| IQ1_M | 18.0 GB | 20.7 GB | Too big | Get file → | |
| IQ2_S | 18.0 GB | 20.7 GB | Too big | Get file → | |
| Q3_K_M | 18.1 GB | 20.7 GB | Too big | Get file → | |
| Q4_K_M | 19.7 GB | 22.3 GB | Too big | Get file → | |
| Q5_K_M | 20.4 GB | 23.0 GB | Too big | Get file → | |
| Q6_K | 22.1 GB | 24.7 GB | Too big | Get file → | |
| Q8_0 | 28.6 GB | 31.2 GB | Too big | Get file → | |
| BF16 | 53.8 GB | 56.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q6_K (est. 4.7 GB at 8 k context). For 16 GB VRAM, Q5_K_M (est. 5.0 GB). For 32 GB VRAM, Q8_0 (est. 5.9 GB). Higher‑quality quants like BF16 require more than 8 GB VRAM.
What GPU do you need for VeriLoop E2?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 5.9 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (6.0 GB file, about 8.7 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (6.0 GB file, about 8.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (20.4 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.6 GB file, about 31.2 GB in use).
Which VeriLoop E2 quant should you choose?
Q4_K_M is the usual starting point for VeriLoop E2: it balances file size and quality well. Here it is a 19.7 GB file.
The Q8_0 file is 3.3 GB, about 0.2 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 Q5_K_M at 2.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about VeriLoop E2
How much VRAM does VeriLoop E2 need?
About 22.3 GB at Q4_K_M with an 8K context window. That is the 19.7 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 VeriLoop E2 on an 8 GB GPU?
Yes, with Q8_0: the 3.3 GB file needs about 5.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of VeriLoop E2 GGUF?
It depends on the quant: Q5_K_M is 2.0 GB, Q6_K is 2.0 GB, Q8_0 is 3.3 GB, BF16 is 6.0 GB, IQ1_M is 18.0 GB, IQ2_S is 18.0 GB and 6 more.
What context length does VeriLoop E2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.
Where can I download VeriLoop E2 GGUF?
The files are on Hugging Face in the tsinghua-sigs-robot-lab/VeriLoop-E2-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 VeriLoop E2 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 VeriLoop E2 on 8 GB VRAM?
Yes, using the Q6_K quantization which estimates 4.7 GB memory at 8 k context.
Does VeriLoop E2 support image inputs?
No, the model has no vision capabilities.