Mochi 2B needs about 2.2 GB of memory at Q4_K_M (a 1.3 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 1.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Mochi 2B – a 1.88B parameter vision‑language model for emotional support
Mochi 2B is a 1.88B parameter model based on Qwen3.5‑2B. It is trained for reasoning, tools, and vision tasks with a focus on emotional support and empathy. The model is released under the apache‑2.0 license.
Good at
- Emotional support and empathy
- Vision‑language reasoning
- Tool usage
Limits
- No vision support in the provided GGUF files
- Large context requires 262144 tokens
- Requires a GPU with sufficient VRAM for chosen quant
Best for
- Chatbots providing mental wellness support
- Vision‑enabled companion apps
- Tool‑integrated assistance
Who it’s for. Developers building empathetic chat interfaces or vision‑enabled support tools. The model is suitable for applications that need a friendly, supportive tone and can handle vision inputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ1_S | 0.7 GB | 1.6 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_XS | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_S | 0.8 GB | 1.7 GB | Fits | Get file → | |
| IQ2_M | 0.9 GB | 1.8 GB | Fits | Get file → | |
| IQ3_XXS | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q2_K_S | 0.9 GB | 1.8 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ3_XS | 1.0 GB | 1.9 GB | Fits | Get file → | |
| IQ3_S | 1.1 GB | 2.0 GB | Fits | Get file → | |
| IQ3_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_0 | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_NL | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q4_1 | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (1.27 GB file, ~2.2 GB memory at 8 k context). If 4 GB VRAM is available, Q3_K_M (1.1 GB file, ~2 GB memory) is a good balance. For very low memory, IQ1_S (0.72 GB file, ~1.6 GB memory) can be used.
What GPU do you need for Mochi 2B?
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 Q6_K (1.6 GB file, about 2.5 GB in use).
Which Mochi 2B quant should you choose?
Q4_K_M is the usual starting point for Mochi 2B: it balances file size and quality well. Here it is a 1.3 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 Mochi 2B
How much VRAM does Mochi 2B need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Mochi 2B on an 8 GB GPU?
Yes, with Q6_K: the 1.6 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mochi 2B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_XS is 0.8 GB, IQ2_S is 0.8 GB and 19 more.
What context length does Mochi 2B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Mochi 2B GGUF?
The files are on Hugging Face in the mradermacher/Mochi-2B-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 Mochi 2B 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 Mochi 2B on 8 GB VRAM?
Yes, the Q4_K_M quant uses about 2.2 GB of VRAM at 8 k context, which fits within an 8 GB GPU.
Does Mochi 2B support vision tasks?
The base model is a vision‑language model, but the provided GGUF files do not include mmproj files for vision.