KafkaLM 15B Base needs about 11.1 GB of memory at Q4_K_M (a 9.5 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 12.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
KafkaLM 15B Base – a 15‑billion‑parameter distilled language model
KafkaLM 15B Base is a 15‑billion‑parameter, sparsity‑aware language model distilled from Mistral‑Small‑24B‑Base‑2501. It supports a 32768‑token context window and is released under the Apache‑2.0 license.
Good at
- High‑capacity language modeling
- Fast inference with pruning
- Low‑memory deployment
Limits
- No vision support
- Requires fine‑tuning for specific tasks
- Large VRAM needed for full precision
Best for
- Research prototyping
- Edge inference with limited GPU
- Fine‑tuning for domain adaptation
Who it’s for. Researchers and developers needing a compact yet powerful language model. The model is ideal for those who can fine‑tune it for specific applications and have access to GPUs with sufficient VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| IQ1_S | 3.6 GB | 5.2 GB | Fits | Get file → | |
| IQ1_M | 4.0 GB | 5.5 GB | Fits | Get file → | |
| IQ2_XXS | 4.5 GB | 6.0 GB | Fits | Get file → | |
| IQ2_XS | 4.9 GB | 6.5 GB | Fits | Get file → | |
| IQ2_S | 5.1 GB | 6.7 GB | Fits | Get file → | |
| IQ2_M | 5.5 GB | 7.1 GB | Fits | Get file → | |
| Q2_K_S | 5.6 GB | 7.2 GB | Fits | Get file → | |
| Q2_K | 6.0 GB | 7.6 GB | Tight | Get file → | |
| IQ3_XXS | 6.2 GB | 7.8 GB | Tight | Get file → | |
| IQ3_XS | 6.7 GB | 8.2 GB | Too big | Get file → | |
| Q3_K_S | 7.0 GB | 8.5 GB | Too big | Get file → | |
| IQ3_S | 7.0 GB | 8.6 GB | Too big | Get file → | |
| IQ3_M | 7.2 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_M | 7.7 GB | 9.3 GB | Too big | Get file → | |
| Q3_K_L | 8.3 GB | 9.8 GB | Too big | Get file → | |
| IQ4_XS | 8.5 GB | 10.1 GB | Too big | Get file → | |
| IQ4_NL | 9.0 GB | 10.6 GB | Too big | Get file → | |
| Q4_0 | 9.0 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_S | 9.0 GB | 10.6 GB | Too big | Get file → | |
| Q4_K_M | 9.5 GB | 11.1 GB | Too big | Get file → | |
| Q4_1 | 9.9 GB | 11.5 GB | Too big | Get file → | |
| Q5_K_S | 10.8 GB | 12.4 GB | Too big | Get file → | |
| Q5_K_M | 11.1 GB | 12.7 GB | Too big | Get file → | |
| Q6_K | 12.8 GB | 14.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (5.2 GB) or IQ1_M (5.5 GB). For 12 GB VRAM, Q4_K_M (11.1 GB) is suitable. Larger GPUs can run Q5_K_M (12.7 GB) or Q6_K (14.4 GB).
What GPU do you need for KafkaLM 15B Base?
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 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_XXS (4.5 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_XXS (6.2 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (9.9 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.8 GB file, about 14.4 GB in use).
Which KafkaLM 15B Base quant should you choose?
Q4_K_M is the usual starting point for KafkaLM 15B Base: it balances file size and quality well. Here it is a 9.5 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 KafkaLM 15B Base
How much VRAM does KafkaLM 15B Base need?
About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.5 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 KafkaLM 15B Base on an 8 GB GPU?
Yes, with IQ3_XXS: the 6.2 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of KafkaLM 15B Base GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.6 GB, IQ1_M is 4.0 GB, IQ2_XXS is 4.5 GB, IQ2_XS is 4.9 GB, IQ2_S is 5.1 GB and 19 more.
What context length does KafkaLM 15B Base 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 KafkaLM 15B Base GGUF?
The files are on Hugging Face in the mradermacher/KafkaLM-15B-Base-i1-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 KafkaLM 15B Base 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 KafkaLM 15B Base on 8 GB VRAM?
Use IQ1_S or IQ1_M quantizations; they require approximately 5.2–5.5 GB of VRAM at 8k context.
Does this model support vision tasks?
No, KafkaLM 15B Base is a text‑only language model.
What license applies to this model?
The model is released under the Apache‑2.0 license.