Toffee 3b Beta needs about 3.7 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 3.2 GB (Q6_K).
Toffee 3b Beta – a 3.83B parameter instruction‑tuned llama model
Toffee 3b Beta is a 3.83B parameter llama model fine‑tuned from mistralai/Ministral‑3‑3B‑Base‑2512 on instructional, mathematical, and programming data. It supports up to 8192 context tokens and is released under the MIT license.
Good at
- Instruction following
- Math reasoning
- Programming assistance
Limits
- No vision support
- Requires 8k context for full performance
- No mixture of experts
Best for
- Chat assistants
- Code generation
- Educational tutoring
Who it’s for. Developers and researchers needing a small, instruction‑tuned language model for local deployment. The model is suitable for applications that require a balance between size and capability.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.4 GB | Fits | Get file → | |
| IQ1_S | 1.1 GB | 2.4 GB | Fits | Get file → | |
| IQ1_M | 1.1 GB | 2.5 GB | Fits | Get file → | |
| IQ2_XXS | 1.2 GB | 2.6 GB | Fits | Get file → | |
| IQ2_XS | 1.3 GB | 2.7 GB | Fits | Get file → | |
| IQ2_S | 1.4 GB | 2.8 GB | Fits | Get file → | |
| IQ2_M | 1.5 GB | 2.9 GB | Fits | Get file → | |
| Q2_K_S | 1.5 GB | 2.9 GB | Fits | Get file → | |
| Q2_K | 1.6 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XXS | 1.6 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XS | 1.8 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 1.8 GB | 3.2 GB | Fits | Get file → | |
| IQ3_S | 1.8 GB | 3.2 GB | Fits | Get file → | |
| IQ3_M | 1.9 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_M | 2.0 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_L | 2.1 GB | 3.5 GB | Fits | Get file → | |
| IQ4_XS | 2.2 GB | 3.5 GB | Fits | Get file → | |
| Q4_0 | 2.3 GB | 3.6 GB | Fits | Get file → | |
| IQ4_NL | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_S | 2.3 GB | 3.7 GB | Fits | Get file → | |
| Q4_K_M | 2.4 GB | 3.7 GB | Fits | Get file → | |
| Q4_1 | 2.5 GB | 3.9 GB | Fits | Get file → | |
| Q5_K_S | 2.7 GB | 4.1 GB | Fits | Get file → | |
| Q5_K_M | 2.8 GB | 4.1 GB | Fits | Get file → | |
| Q6_K | 3.2 GB | 4.5 GB | Fits | Get file → |
For 8 GB VRAM use IQ1_S (1.07 GB, 2.4 GB RAM). For 12 GB VRAM use Q4_K_M (2.37 GB, 3.7 GB RAM). For 16 GB VRAM use Q5_K_M (2.75 GB, 4.1 GB RAM). Estimates are approximate.
What GPU do you need for Toffee 3b Beta?
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 Q4_1 (2.5 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.2 GB file, about 4.5 GB in use).
Which Toffee 3b Beta quant should you choose?
Q4_K_M is the usual starting point for Toffee 3b Beta: it balances file size and quality well. Here it is a 2.4 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 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 Toffee 3b Beta
How much VRAM does Toffee 3b Beta need?
About 3.7 GB at Q4_K_M with an 8K context window. That is the 2.4 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 Toffee 3b Beta on an 8 GB GPU?
Yes, with Q6_K: the 3.2 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Toffee 3b Beta GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.1 GB, IQ1_M is 1.1 GB, IQ2_XXS is 1.2 GB, IQ2_XS is 1.3 GB, IQ2_S is 1.4 GB and 19 more.
What context length does Toffee 3b Beta support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.
Where can I download Toffee 3b Beta GGUF?
The files are on Hugging Face in the mradermacher/toffee-3b-beta-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 Toffee 3b Beta 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 Toffee 3b Beta on 8 GB VRAM?
Yes, the IQ1_S quant uses 1.07 GB file size and requires about 2.4 GB RAM at 8k context.
Does the model support vision tasks?
No, Toffee 3b Beta is a text‑only model.
What license does it use?
The model is released under the MIT license.