bagel dpo 20b v04 i1 needs about 14.8 GB of memory at Q4_K_M (a 12.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 5.3 GB (IQ1_S) to 17.0 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Bagel DPO 20B v04 i1 – 20B internlm2 fine‑tuned with direct preference optimization
Bagel DPO 20B v04 i1 is a 20B parameter internlm2 model fine‑tuned using DPO. It supports coding, roleplay, and tools. The model was trained on 32,768 context tokens and uses a custom quantization set.
Good at
- Coding tasks
- Roleplay interactions
- Tool usage
Limits
- No vision support
- License is other
- Requires large VRAM for higher quants
Best for
- Developers needing coding assistance
- Chatbot developers for roleplay
- Tool‑integrated LLM applications
Who it’s for. Engineers and researchers who want a 20B internlm2 model with DPO fine‑tuning for text‑only tasks. The model is suitable for developers building chat or coding assistants that require advanced instruction following.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 5.3 GB | 7.4 GB | Tight | Get file → | |
| IQ1_M | 5.7 GB | 7.8 GB | Tight | Get file → | |
| IQ2_XXS | 6.3 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 6.8 GB | 9.0 GB | Too big | Get file → | |
| IQ2_S | 7.2 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 7.7 GB | 9.8 GB | Too big | Get file → | |
| Q2_K | 8.2 GB | 10.3 GB | Too big | Get file → | |
| IQ3_XXS | 8.6 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XS | 9.0 GB | 11.1 GB | Too big | Get file → | |
| Q3_K_S | 9.4 GB | 11.5 GB | Too big | Get file → | |
| IQ3_S | 9.5 GB | 11.6 GB | Too big | Get file → | |
| IQ3_M | 9.8 GB | 11.9 GB | Too big | Get file → | |
| Q3_K_M | 10.4 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_L | 11.2 GB | 13.3 GB | Too big | Get file → | |
| IQ4_XS | 11.4 GB | 13.5 GB | Too big | Get file → | |
| Q4_0 | 12.0 GB | 14.1 GB | Too big | Get file → | |
| Q4_K_S | 12.1 GB | 14.2 GB | Too big | Get file → | |
| Q4_K_M | 12.7 GB | 14.8 GB | Too big | Get file → | |
| Q5_K_S | 14.4 GB | 16.5 GB | Too big | Get file → | |
| Q5_K_M | 14.7 GB | 16.9 GB | Too big | Get file → | |
| Q6_K | 17.0 GB | 19.1 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 5.29 GB, estimated 7.4 GB memory). For 12 GB VRAM, IQ2_XS (6.85 GB, 9 GB memory) or Q2_K (8.22 GB, 10.3 GB memory). For 16 GB VRAM, Q3_K_M (10.39 GB, 12.5 GB memory) or Q4_K_M (12.66 GB, 14.8 GB memory).
What GPU do you need for bagel dpo 20b v04 i1?
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: no quant fits at an 8K context.
- 8 GB VRAM: the best quant that fits is IQ1_M (5.7 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is IQ3_M (9.8 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (12.7 GB file, about 14.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (17.0 GB file, about 19.1 GB in use).
Which bagel dpo 20b v04 i1 quant should you choose?
Q4_K_M is the usual starting point for bagel dpo 20b v04 i1: it balances file size and quality well. Here it is a 12.7 GB file.
If memory is tight, the smallest file is IQ1_S at 5.3 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 bagel dpo 20b v04 i1
How much VRAM does bagel dpo 20b v04 i1 need?
About 14.8 GB at Q4_K_M with an 8K context window. That is the 12.7 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 bagel dpo 20b v04 i1 on an 8 GB GPU?
Yes, with IQ1_M: the 5.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of bagel dpo 20b v04 i1 GGUF?
It depends on the quant: IQ1_S is 5.3 GB, IQ1_M is 5.7 GB, IQ2_XXS is 6.3 GB, IQ2_XS is 6.8 GB, IQ2_S is 7.2 GB, IQ2_M is 7.7 GB and 15 more.
What context length does bagel dpo 20b v04 i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.
Where can I download bagel dpo 20b v04 i1 GGUF?
The files are on Hugging Face in the mradermacher/bagel-dpo-20b-v04-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 bagel dpo 20b v04 i1 use?
Hugging Face lists the license as other. 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, the IQ1_S quant uses 5.29 GB file size and estimates 7.4 GB VRAM at 8 k context.
Does this model support image inputs?
No, the model has no vision capability.
What is the context length of this model?
The model was trained with a context length of 32,768 tokens.