blossom 40B needs about 26.8 GB of memory at Q4_K_M (a 24.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 14 quants, from 14.9 GB (Q2_K) to 42.5 GB (Q8_0).
Blossom 40B – a 40‑billion‑parameter LLaMA‑based model
Blossom 40B is a 40‑billion‑parameter LLaMA architecture model trained with a 4096‑token context. It is released under the Apache‑2.0 license and available in multiple GGUF quantizations.
Good at
- Large‑scale text generation
- Contextual understanding up to 4096 tokens
- High‑capacity language modeling
Limits
- No vision support
- Requires significant VRAM for higher quants
- No mixture of experts
Best for
- Research prototypes needing large context
- Enterprise chatbots with high token limits
- Custom fine‑tuning on local hardware
Who it’s for. Developers and researchers who need a large LLaMA‑based model for text‑only tasks and can manage the memory requirements. The model is suitable for local deployment with sufficient GPU resources.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 14.9 GB | 16.5 GB | Too big | Get file → | |
| IQ3_XS | 16.5 GB | 18.2 GB | Too big | Get file → | |
| Q3_K_S | 17.4 GB | 19.0 GB | Too big | Get file → | |
| IQ3_S | 17.4 GB | 19.1 GB | Too big | Get file → | |
| IQ3_M | 18.1 GB | 19.7 GB | Too big | Get file → | |
| Q3_K_M | 19.3 GB | 21.0 GB | Too big | Get file → | |
| Q3_K_L | 21.1 GB | 22.7 GB | Too big | Get file → | |
| IQ4_XS | 21.6 GB | 23.3 GB | Too big | Get file → | |
| Q4_K_S | 22.8 GB | 24.4 GB | Too big | Get file → | |
| Q4_K_M | 24.0 GB | 25.6 GB | Too big | Get file → | |
| Q5_K_S | 27.5 GB | 29.2 GB | Too big | Get file → | |
| Q5_K_M | 28.2 GB | 29.9 GB | Too big | Get file → | |
| Q6_K | 32.8 GB | 34.5 GB | Too big | Get file → | |
| Q8_0 | 42.5 GB | 44.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (14.87 GB file, 17.7 GB memory) or IQ3_XS (16.5 GB file, 19.4 GB memory). For 12 GB VRAM, Q3_K_S (17.36 GB file, 20.2 GB memory) or IQ3_S (17.43 GB file, 20.3 GB memory) are suitable. Larger quants require more VRAM.
What GPU do you need for blossom 40B?
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 Q3_K_L (21.1 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (28.2 GB file, about 31.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (42.5 GB file, about 45.3 GB in use).
Which blossom 40B quant should you choose?
Q4_K_M is the usual starting point for blossom 40B: it balances file size and quality well. Here it is a 24.0 GB file.
The Q8_0 file is 42.5 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.
If memory is tight, the smallest file is Q2_K at 14.9 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 blossom 40B
How much VRAM does blossom 40B need?
About 26.8 GB at Q4_K_M with an 8K context window. That is the 24.0 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 blossom 40B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of blossom 40B GGUF?
It depends on the quant: Q2_K is 14.9 GB, IQ3_XS is 16.5 GB, Q3_K_S is 17.4 GB, IQ3_S is 17.4 GB, IQ3_M is 18.1 GB, Q3_K_M is 19.3 GB and 8 more.
What context length does blossom 40B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.3 GB at 8K and 1.2 GB at 4K.
Where can I download blossom 40B GGUF?
The files are on Hugging Face in the mradermacher/blossom-40B-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 blossom 40B 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 Blossom 40B on 8 GB VRAM?
Yes, using the Q2_K quantization which estimates 17.7 GB memory at 8k context. It is the smallest quant available.
Does Blossom 40B support vision tasks?
No, the model has no vision capabilities.