L3.1 Blackholev2 12B needs about 9.5 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 9.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 6.7 GB.
12B‑parameter Llama‑style model with multiple quant options
L3.1 Blackholev2 12B is a 12‑billion‑parameter Llama architecture model. It offers a range of quantizations from IQ1_S to Q6_K, enabling deployment on various hardware configurations. The model supports a trained context of 2,146,304 tokens.
Good at
- Large context handling
- Flexible quantization
- High token capacity
Limits
- No license information provided
- No vision support
- Large memory for higher quants
Best for
- Long‑form text generation
- Context‑heavy dialogue
- Research prototyping
Who it’s for. Developers and researchers needing a large‑scale Llama model with adjustable memory footprints. Suitable for environments where GPU memory is a constraint and quantization trade‑offs are acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 2.2 GB | Fits | Get file → | |
| IQ1_S | 2.8 GB | 5.0 GB | Fits | Get file → | |
| IQ1_M | 3.1 GB | 5.2 GB | Fits | Get file → | |
| IQ2_XXS | 3.4 GB | 5.6 GB | Fits | Get file → | |
| IQ2_XS | 3.8 GB | 5.9 GB | Fits | Get file → | |
| IQ2_S | 4.0 GB | 6.2 GB | Fits | Get file → | |
| IQ2_M | 4.3 GB | 6.4 GB | Fits | Get file → | |
| Q2_K_S | 4.3 GB | 6.5 GB | Fits | Get file → | |
| Q2_K | 4.6 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XXS | 4.8 GB | 7.0 GB | Fits | Get file → | |
| IQ3_XS | 5.1 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_S | 5.4 GB | 7.5 GB | Tight | Get file → | |
| IQ3_S | 5.4 GB | 7.6 GB | Tight | Get file → | |
| IQ3_M | 5.5 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_M | 5.9 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_L | 6.4 GB | 8.6 GB | Too big | Get file → | |
| IQ4_XS | 6.5 GB | 8.7 GB | Too big | Get file → | |
| Q4_0 | 6.9 GB | 9.1 GB | Too big | Get file → | |
| IQ4_NL | 6.9 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 9.5 GB | Too big | Get file → | |
| Q4_1 | 7.6 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_S | 8.3 GB | 10.5 GB | Too big | Get file → | |
| Q5_K_M | 8.5 GB | 10.7 GB | Too big | Get file → | |
| Q6_K | 9.8 GB | 12.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.85 GB file, 5 GB memory) or Q2_XXS (3.44 GB file, 5.6 GB memory). With 12 GB VRAM, Q4_K_M (7.28 GB file, 9.5 GB memory) or Q5_K_M (8.51 GB file, 10.7 GB memory) are viable. Higher quants require more memory.
What GPU do you need for L3.1 Blackholev2 12B?
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 the main file (0.0 GB file, about 2.2 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_XS (3.8 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_M (5.5 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (9.8 GB file, about 12.0 GB in use).
Which L3.1 Blackholev2 12B quant should you choose?
Q4_K_M is the usual starting point for L3.1 Blackholev2 12B: it balances file size and quality well. Here it is a 7.3 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about L3.1 Blackholev2 12B
How much VRAM does L3.1 Blackholev2 12B need?
About 9.5 GB at Q4_K_M with an 8K context window. That is the 7.3 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 L3.1 Blackholev2 12B on an 8 GB GPU?
Yes, with IQ3_M: the 5.5 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of L3.1 Blackholev2 12B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.8 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.4 GB, IQ2_XS is 3.8 GB, IQ2_S is 4.0 GB and 19 more.
What context length does L3.1 Blackholev2 12B support?
The GGUF header lists a trained context length of 2,146,304 tokens (2096K). The KV cache grows with the context you use: about 1.7 GB at 8K and 6.7 GB at 32K.
Where can I download L3.1 Blackholev2 12B GGUF?
The files are on Hugging Face in the mradermacher/L3.1-Blackholev2-12B-i1-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 this model on 8 GB VRAM?
Yes, using IQ1_S or Q2_XXS quants, which estimate 5–5.6 GB memory at 8k context.
What is the context length of this model?
The model was trained with a context of 2,146,304 tokens.
Does this model support vision tasks?
No, the model does not include vision capabilities.