Topxtral-4x7B-v0.1 needs about 12.8 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 22 quants, from 0.0 GB (Q5_0) to 11.2 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
18.5B parameter Topxtral model with 32k context
Topxtral-4x7B-v0.1 is a 18.5B parameter llama architecture model. It supports a 32768 token context window and is a mixture of experts. The model is available in multiple GGUF quantizations.
Good at
- Large context handling
- Mixture of experts inference
- High parameter count
Limits
- No license specified
- No vision support
- Requires 8k context memory estimates
Best for
- Long-form text generation
- Complex reasoning tasks
- Fine-tuning with large context
Who it’s for. Developers and researchers needing a large llama model with extended context. Suitable for local deployment via llama.cpp with appropriate quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_0 | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_1 | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_M | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q5_K_S | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q6_K | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q2_K | 6.8 GB | 8.4 GB | Too big | Get file → | |
| IQ3_XS | 7.6 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_S | 8.0 GB | 9.6 GB | Too big | Get file → | |
| IQ3_S | 8.0 GB | 9.6 GB | Too big | Get file → | |
| IQ3_M | 8.2 GB | 9.8 GB | Too big | Get file → | |
| Q3_K | 8.9 GB | 10.5 GB | Too big | Get file → | |
| Q3_K_M | 8.9 GB | 10.5 GB | Too big | Get file → | |
| Q4_1 | 9.1 GB | 10.7 GB | Too big | Get file → | |
| Q3_K_L | 9.6 GB | 11.2 GB | Too big | Get file → | |
| IQ4_XS | 10.0 GB | 11.6 GB | Too big | Get file → | |
| Q4_0 | 10.5 GB | 12.0 GB | Too big | Get file → | |
| Q4_K_S | 10.5 GB | 12.1 GB | Too big | Get file → | |
| IQ4_NL | 10.6 GB | 12.1 GB | Too big | Get file → | |
| Q4_K | 11.2 GB | 12.8 GB | Too big | Get file → | |
| Q4_K_M | 11.2 GB | 12.8 GB | Too big | Get file → |
For 8GB VRAM, use Q5_0 or Q5_1 (≈1.6 GB memory). For 16GB VRAM, Q4_0 or Q4_K (≈12 GB memory). For 32GB VRAM, Q3_K or Q3_K_M (≈10–11 GB memory). Estimates are approximate.
What GPU do you need for Topxtral-4x7B-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: the best quant that fits is Q5_0 (0.0 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_0 (0.0 GB file, about 1.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_0 (0.0 GB file, about 1.6 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (10.5 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K (11.2 GB file, about 12.8 GB in use).
Which Topxtral-4x7B-v0.1 quant should you choose?
Q4_K_M is the usual starting point for Topxtral-4x7B-v0.1: it balances file size and quality well. Here it is a 11.2 GB file.
The Q8_0 file is 0.0 GB, about 0.0 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 Q5_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about Topxtral-4x7B-v0.1
How much VRAM does Topxtral-4x7B-v0.1 need?
About 12.8 GB at Q4_K_M with an 8K context window. That is the 11.2 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 Topxtral-4x7B-v0.1 on an 8 GB GPU?
Yes, with Q5_0: the 0.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Topxtral-4x7B-v0.1 GGUF?
It depends on the quant: Q5_0 is 0.0 GB, Q5_1 is 0.0 GB, Q5_K is 0.0 GB, Q5_K_M is 0.0 GB, Q5_K_S is 0.0 GB, Q6_K is 0.0 GB and 16 more.
What context length does Topxtral-4x7B-v0.1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Topxtral-4x7B-v0.1 GGUF?
The files are on Hugging Face in the RichardErkhov/MaziyarPanahi_-_Topxtral-4x7B-v0.1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Topxtral-4x7B-v0.1 on 8 GB VRAM?
Yes, using Q5_0 or Q5_1 quantizations which require about 1.6 GB memory at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports a 32768 token context window.