jpacifico Chocolatine 14B Instruct DPO v1.2 needs about 10.7 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 5.1 GB (Q2_K) to 14.8 GB (Q8_0).
14B Phi‑3 Instruct model fine‑tuned for French and English
Chocolatine 14B Instruct DPO v1.2 is a Phi‑3‑based LLM with 14B parameters. It was fine‑tuned with a French‑ORCA DPO dataset and supports a 4k token context window. The model is released under the MIT license.
Good at
- Strong French language handling
- Good English performance after French fine‑tuning
- Supports 4k token context
Limits
- No moderation mechanism
- No vision support
- Requires 8k context for memory estimates
Best for
- French‑centric content creation
- English‑French bilingual dialogue
- Fine‑tuned instruction following
Who it’s for. Developers and researchers needing a 14B Phi‑3 model with robust French and English capabilities. The model is suitable for local deployment via llama.cpp and is free under MIT.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 5.1 GB | 6.5 GB | Fits | Get file → | |
| IQ3_XS | 5.8 GB | 7.1 GB | Fits | Get file → | |
| IQ3_S | 6.1 GB | 7.4 GB | Tight | Get file → | |
| Q3_K_S | 6.1 GB | 7.4 GB | Tight | Get file → | |
| IQ3_M | 6.5 GB | 7.8 GB | Tight | Get file → | |
| Q3_K | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_M | 6.9 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_L | 7.5 GB | 8.8 GB | Too big | Get file → | |
| IQ4_XS | 7.5 GB | 8.9 GB | Too big | Get file → | |
| Q4_0 | 7.9 GB | 9.2 GB | Too big | Get file → | |
| IQ4_NL | 8.0 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_S | 8.0 GB | 9.3 GB | Too big | Get file → | |
| Q4_K | 8.6 GB | 9.9 GB | Too big | Get file → | |
| Q4_K_M | 8.6 GB | 9.9 GB | Too big | Get file → | |
| Q4_1 | 8.8 GB | 10.1 GB | Too big | Get file → | |
| Q5_0 | 9.6 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_S | 9.6 GB | 11.0 GB | Too big | Get file → | |
| Q5_K | 10.1 GB | 11.4 GB | Too big | Get file → | |
| Q5_K_M | 10.1 GB | 11.4 GB | Too big | Get file → | |
| Q5_1 | 10.5 GB | 11.8 GB | Too big | Get file → | |
| Q6_K | 11.5 GB | 12.8 GB | Too big | Get file → | |
| Q8_0 | 14.8 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (5.14 GB file, 7.3 GB memory) or IQ3_XS (5.81 GB file, 8 GB memory). For 12 GB VRAM, Q4_K (8.57 GB file, 10.7 GB memory) or Q5_K (10.07 GB file, 12.3 GB memory) are suitable. Larger VRAM allows higher‑quality quants like Q5_K_M or Q6_K.
What GPU do you need for jpacifico Chocolatine 14B Instruct DPO v1.2?
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 IQ3_XS (5.8 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_0 (9.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (11.5 GB file, about 13.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
Which jpacifico Chocolatine 14B Instruct DPO v1.2 quant should you choose?
Q4_K_M is the usual starting point for jpacifico Chocolatine 14B Instruct DPO v1.2: it balances file size and quality well. Here it is a 8.6 GB file.
The Q8_0 file is 14.8 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 5.1 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
Frequently asked questions about jpacifico Chocolatine 14B Instruct DPO v1.2
How much VRAM does jpacifico Chocolatine 14B Instruct DPO v1.2 need?
About 10.7 GB at Q4_K_M with an 8K context window. That is the 8.6 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 jpacifico Chocolatine 14B Instruct DPO v1.2 on an 8 GB GPU?
Yes, with IQ3_XS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of jpacifico Chocolatine 14B Instruct DPO v1.2 GGUF?
It depends on the quant: Q2_K is 5.1 GB, IQ3_XS is 5.8 GB, IQ3_S is 6.1 GB, Q3_K_S is 6.1 GB, IQ3_M is 6.5 GB, Q3_K is 6.9 GB and 16 more.
What context length does jpacifico Chocolatine 14B Instruct DPO v1.2 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.
Where can I download jpacifico Chocolatine 14B Instruct DPO v1.2 GGUF?
The files are on Hugging Face in the RichardErkhov/jpacifico_-_Chocolatine-14B-Instruct-DPO-v1.2-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 jpacifico Chocolatine 14B Instruct DPO v1.2 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 Chocolatine on 8 GB VRAM?
Yes, using the Q2_K or IQ3_XS quantized files will fit within 8 GB VRAM with approximate memory usage of 7.3–8 GB.
Does the model support vision tasks?
No, the model is purely text‑generation and has no vision capabilities.
Is there a moderation filter in the model?
No, the model does not include a moderation mechanism.