Normistral 11b Thinking 4 needs about 8.7 GB of memory at Q4_K_M (a 6.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 7 quants, from 6.9 GB (Q4_K_M) to 22.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Normistral 11b Thinking 4 – instruction‑tuned Norwegian LLM
Normistral 11b Thinking 4 is a 11.4 billion parameter llama‑style model tuned for reasoning tasks. It is released under Apache 2.0 and available in multiple GGUF quantizations. The model supports up to 1 024 000 context tokens.
Good at
- Reasoning
- Instruction following
- Norwegian language
Limits
- No vision support
- Large VRAM needed for higher quantizations
- License is Apache 2.0
Best for
- Chatbots needing reasoning
- Local inference on powerful GPUs
- Educational tools for Norwegian
Who it’s for. Developers and researchers who need a Norwegian‑focused reasoning model. The model is free to use and can be run locally with llama.cpp or ollama.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 6.9 GB | 8.7 GB | Too big | Get file → | |
| Q5_0 | 7.9 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_M | 8.1 GB | 9.9 GB | Too big | Get file → | |
| Q6_K | 9.4 GB | 11.2 GB | Too big | Get file → | |
| Q8_0 | 12.1 GB | 14.0 GB | Too big | Get file → | |
| BF16 | 22.9 GB | 24.7 GB | Too big | Get file → | |
| F16 | 22.9 GB | 24.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (6.91 GB file, ~8.7 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (8.1 GB file, ~9.9 GB memory). For 16 GB VRAM, Q6_K (9.38 GB file, ~11.2 GB memory).
What GPU do you need for Normistral 11b Thinking 4?
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: the best quant that fits is Q6_K (9.4 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (12.1 GB file, about 14.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.1 GB file, about 14.0 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (22.9 GB file, about 24.7 GB in use).
Which Normistral 11b Thinking 4 quant should you choose?
Q4_K_M is the usual starting point for Normistral 11b Thinking 4: it balances file size and quality well. Here it is a 6.9 GB file.
The Q8_0 file is 12.1 GB, about 1.8 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Normistral 11b Thinking 4
How much VRAM does Normistral 11b Thinking 4 need?
About 8.7 GB at Q4_K_M with an 8K context window. That is the 6.9 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 Normistral 11b Thinking 4 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Normistral 11b Thinking 4 GGUF?
It depends on the quant: Q4_K_M is 6.9 GB, Q5_0 is 7.9 GB, Q5_K_M is 8.1 GB, Q6_K is 9.4 GB, Q8_0 is 12.1 GB, BF16 is 22.9 GB and 1 more.
What context length does Normistral 11b Thinking 4 support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Normistral 11b Thinking 4 GGUF?
The files are on Hugging Face in the ltg/normistral-11b-thinking-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 Normistral 11b Thinking 4 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 8.7 GB memory at 8k context, which fits 8 GB VRAM with some overhead.
Does the model support vision tasks?
No, the model is purely text‑based and does not include vision capabilities.
What license applies to the model weights?
The weights are released under the Apache 2.0 license, with no additional restrictions.