Carbon 8B needs about 7.1 GB of memory at Q4_K_M (a 5.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 5.5 GB (Q4_K_M) to 16.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Carbon 8B – 8B‑parameter DNA language model with 32k token context
Carbon 8B is an 8B‑parameter decoder‑only autoregressive model trained on DNA and RNA sequences, primarily eukaryotic. It uses a hybrid 6‑mer DNA tokenizer and a Qwen3 BPE for English text. The model supports a native context of 32,768 tokens (~196 kbp) and can be extended to 128k tokens with YaRN.
Good at
- Long‑context DNA generation
- Base‑pair‑level scoring via per‑token log‑probabilities
- Hybrid DNA‑text tokenization
Limits
- No instruction tuning or vision support
- Requires recent llama.cpp with HybridDNATokenizer
- License is Apache‑2.0
Best for
- DNA sequence completion
- Per‑sequence likelihood scoring
- Speculative decoding with 500M draft
Who it’s for. Researchers and developers needing high‑capacity DNA language modeling. Suitable for tasks that require long context and precise base‑pair control, such as genome design or variant analysis.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q5_K_M | 6.3 GB | 7.9 GB | Tight | Get file → | |
| Q6_K | 7.1 GB | 8.7 GB | Too big | Get file → | |
| Q8_0 | 8.8 GB | 10.4 GB | Too big | Get file → | |
| BF16 | 16.5 GB | 18.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.55 GB, ~7.1 GB RAM). If 12 GB VRAM is available, Q5_K_M (6.29 GB, ~7.9 GB RAM) offers better precision. For 16 GB VRAM, Q6_K (7.09 GB, ~8.7 GB RAM) or Q8_0 (8.78 GB, ~10.4 GB RAM) can be used, depending on desired accuracy.
What GPU do you need for Carbon 8B?
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: the best quant that fits is Q5_K_M (6.3 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.8 GB file, about 10.4 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (16.5 GB file, about 18.1 GB in use).
Which Carbon 8B quant should you choose?
Q4_K_M is the usual starting point for Carbon 8B: it balances file size and quality well. Here it is a 5.5 GB file.
The Q8_0 file is 8.8 GB, about 1.6 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 Carbon 8B
How much VRAM does Carbon 8B need?
About 7.1 GB at Q4_K_M with an 8K context window. That is the 5.5 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 Carbon 8B on an 8 GB GPU?
Yes, with Q5_K_M: the 6.3 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Carbon 8B GGUF?
It depends on the quant: Q4_K_M is 5.5 GB, Q5_K_M is 6.3 GB, Q6_K is 7.1 GB, Q8_0 is 8.8 GB, BF16 is 16.5 GB.
What context length does Carbon 8B 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 Carbon 8B GGUF?
The files are on Hugging Face in the HuggingFaceBio/Carbon-8B-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 Carbon 8B 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 Carbon 8B on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which requires about 7.1 GB of RAM at 8k context.
Does Carbon 8B support image inputs?
No, it is a base DNA model without vision capabilities.
What context length does Carbon 8B support natively?
It natively supports 32,768 tokens (~196 kbp) and can be extended to 128k tokens with YaRN.