Swallow MX 8x7b NVE v0.1 needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 14 quants, from 17.3 GB (Q2_K) to 49.6 GB (Q8_0).
Swallow MX 8x7b NVE v0.1 – 46.7B parameter Japanese/English Llama model
Swallow MX 8x7b NVE v0.1 is a 46.7B parameter Llama‑style model trained from Mixtral‑8x7B‑Instruct‑v0.1 with added Japanese data. It supports 4096 token context and is released under apache‑2.0. The model is available in multiple GGUF quantizations.
Good at
- Japanese and English text generation
- Large context handling
- Mixture of experts architecture
Limits
- No vision support
- Requires 8k context for memory estimates
- Early research stage, no safety tuning
Best for
- Japanese language chatbots
- Multilingual content creation
- Research prototyping
Who it’s for. Developers and researchers needing a large Japanese/English LLM with a 46.7B parameter count. The model is suitable for experimentation and prototyping in a research environment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 17.3 GB | 18.3 GB | Too big | Get file → | |
| IQ3_XS | 19.4 GB | 20.4 GB | Too big | Get file → | |
| IQ3_S | 20.4 GB | 21.5 GB | Too big | Get file → | |
| Q3_K_S | 20.4 GB | 21.5 GB | Too big | Get file → | |
| IQ3_M | 21.4 GB | 22.5 GB | Too big | Get file → | |
| Q3_K_M | 22.5 GB | 23.6 GB | Too big | Get file → | |
| Q3_K_L | 24.2 GB | 25.2 GB | Too big | Get file → | |
| IQ4_XS | 25.4 GB | 26.4 GB | Too big | Get file → | |
| Q4_K_S | 26.7 GB | 27.8 GB | Too big | Get file → | |
| Q4_K_M | 28.4 GB | 29.5 GB | Too big | Get file → | |
| Q5_K_S | 32.2 GB | 33.3 GB | Too big | Get file → | |
| Q5_K_M | 33.2 GB | 34.3 GB | Too big | Get file → | |
| Q6_K | 38.4 GB | 39.4 GB | Too big | Get file → | |
| Q8_0 | 49.6 GB | 50.7 GB | Too big | Get file → |
For 8 GB VRAM use Q2_K (18.9 GB memory). For 12 GB VRAM use Q3_K_S (22 GB memory). For 16 GB VRAM use Q4_K_M (30 GB memory). Estimates are approximate.
What GPU do you need for Swallow MX 8x7b NVE v0.1?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).
Which Swallow MX 8x7b NVE v0.1 quant should you choose?
Q4_K_M is the usual starting point for Swallow MX 8x7b NVE v0.1: it balances file size and quality well. Here it is a 28.4 GB file.
The Q8_0 file is 49.6 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 17.3 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 Swallow MX 8x7b NVE v0.1
How much VRAM does Swallow MX 8x7b NVE v0.1 need?
About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 Swallow MX 8x7b NVE v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Swallow MX 8x7b NVE v0.1 GGUF?
It depends on the quant: Q2_K is 17.3 GB, IQ3_XS is 19.4 GB, IQ3_S is 20.4 GB, Q3_K_S is 20.4 GB, IQ3_M is 21.4 GB, Q3_K_M is 22.5 GB and 8 more.
What context length does Swallow MX 8x7b NVE v0.1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.
Where can I download Swallow MX 8x7b NVE v0.1 GGUF?
The files are on Hugging Face in the mradermacher/Swallow-MX-8x7b-NVE-v0.1-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 Swallow MX 8x7b NVE v0.1 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 Swallow MX 8x7b NVE v0.1 on 8 GB VRAM?
Use the Q2_K quant which estimates 18.9 GB memory at 8k context, so 8 GB VRAM is insufficient.
Does this model support vision tasks?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.