bagel dpo 20b v04 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 15 quants, from 8.2 GB (Q2_K) to 39.7 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.
Bagel DPO 20B v04 – 19.9B internlm2 fine‑tuned with DPO
Bagel DPO 20B v04 is a 19.9B parameter internlm2 model fine‑tuned with direct preference optimization. It supports coding, roleplay, and tools. The model is available in multiple GGUF quantizations.
Good at
- Coding with Python datasets
- Roleplay from Bluemoon and ShareGPT
- Tool‑calling via GlaiveAI dataset
Limits
- No vision support
- Requires 8k context for memory estimates
- License is other, not standard
Best for
- Developers building coding assistants
- Chatbots needing roleplay dialogue
- Applications that call external tools
Who it’s for. Engineers and researchers who need a large internlm2 model with DPO fine‑tuning for text‑only tasks. The model is suitable for local deployment using llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 8.2 GB | 10.3 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 | 11.5 GB | 13.6 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 → | |
| Q8_0 | 21.6 GB | 23.8 GB | Too big | Get file → | |
| — | 39.7 GB | 41.8 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (8.22 GB, ~10.3 GB RAM). For 12 GB VRAM, Q4_K_M (12.66 GB, ~14.8 GB RAM). For 16 GB VRAM, Q5_K_M (14.75 GB, ~16.9 GB RAM). Memory estimates are approximate.
What GPU do you need for bagel dpo 20b v04?
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: no quant fits at an 8K context.
- 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 Q8_0 (21.6 GB file, about 23.8 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (21.6 GB file, about 23.8 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (39.7 GB file, about 41.8 GB in use).
Which bagel dpo 20b v04 quant should you choose?
Q4_K_M is the usual starting point for bagel dpo 20b v04: it balances file size and quality well. Here it is a 12.7 GB file.
The Q8_0 file is 21.6 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 8.2 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
How much VRAM does bagel dpo 20b v04 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 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of bagel dpo 20b v04 GGUF?
It depends on the quant: Q2_K is 8.2 GB, IQ3_XS is 9.0 GB, Q3_K_S is 9.4 GB, IQ3_S is 9.5 GB, IQ3_M is 9.8 GB, Q3_K_M is 10.4 GB and 9 more.
What context length does bagel dpo 20b v04 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 GGUF?
The files are on Hugging Face in the mradermacher/bagel-dpo-20b-v04-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 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 Bagel DPO 20B v04 on 8 GB VRAM?
Yes, using the Q2_K quantization which is 8.22 GB and requires about 10.3 GB RAM at 8k context.
Does this model support image inputs?
No, the model has no vision capabilities.
What is the maximum context length?
The model was trained with 32768 tokens and supports up to that context length.