norbloom 7b scratch needs about 9.1 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 3.5 GB (Q3_K_M) to 7.1 GB (Q8_0).
NorBLOOM‑7b‑scratch: a 7 billion‑parameter Norwegian BLOOM model
NorBLOOM‑7b‑scratch is a 7 billion‑parameter BLOOM architecture model trained from scratch on 260 billion subword tokens of Norwegian text. It supports coding tasks and runs with the llama.cpp runtime. The model is licensed under Apache‑2.0.
Good at
- Norwegian language generation
- Coding assistance
- Text completion
Limits
- No vision support
- Context limited to 4096 tokens
- Requires at least 8 GB VRAM for Q4_K_M
Best for
- Developers building Norwegian chatbots
- Researchers testing Norwegian language models
- Educators creating coding tutorials
Who it’s for. This model is suited for developers and researchers who need a Norwegian‑focused language model for text generation or coding tasks. It is ideal for projects that can run llama.cpp and have sufficient GPU memory.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 3.5 GB | 6.2 GB | Fits | Get file → | |
| Q4_K_M | 4.3 GB | 6.9 GB | Fits | Get file → | |
| Q5_K_M | 5.0 GB | 7.6 GB | Tight | Get file → | |
| Q6_K | 5.5 GB | 8.2 GB | Too big | Get file → | |
| Q8_0 | 7.1 GB | 9.8 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 4.3 GB, estimated 9.1 GB memory). For 12 GB VRAM use Q5_K_M (5 GB, 9.8 GB memory). For 16 GB VRAM use Q6_K (5.51 GB, 10.3 GB memory).
What GPU do you need for norbloom 7b scratch?
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 Q8_0 (7.1 GB file, about 11.9 GB in use).
Which norbloom 7b scratch quant should you choose?
Q4_K_M is the usual starting point for norbloom 7b scratch: it balances file size and quality well. Here it is a 4.3 GB file.
The Q8_0 file is 7.1 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 Q3_K_M at 3.5 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about norbloom 7b scratch
How much VRAM does norbloom 7b scratch need?
About 9.1 GB at Q4_K_M with an 8K context window. That is the 4.3 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 norbloom 7b scratch on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of norbloom 7b scratch GGUF?
It depends on the quant: Q3_K_M is 3.5 GB, Q4_K_M is 4.3 GB, Q5_K_M is 5.0 GB, Q6_K is 5.5 GB, Q8_0 is 7.1 GB.
What context length does norbloom 7b scratch support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download norbloom 7b scratch GGUF?
The files are on Hugging Face in the ltg/norbloom-7b-scratch repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does norbloom 7b scratch 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 NorBLOOM‑7b‑scratch on 8 GB VRAM?
Yes, the Q4_K_M quantized file uses about 9.1 GB memory at 8 k context, which fits within 8 GB VRAM with some overhead.
Does this model support image inputs?
No, NorBLOOM‑7b‑scratch does not have vision capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license.