KA

KafkaLM 15B

KafkalmGGUF by mradermacherUpdated 2025-12-23
Download on Hugging Face
Parameters15.6B
Context32K
Layers32
Architecturellama
Smallest quant0.0 GB
Quick answer

KafkaLM 15B 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 – 15‑billion‑parameter distilled language model

KafkaLM 15B is a 15‑billion‑parameter language model distilled from Mistral‑Small‑24B‑Base‑2501. It supports a 32768‑token context window and is licensed under apache‑2.0.

Good at

  • Large context inference
  • High token throughput
  • Sparsity‑aware performance

Limits

  • No vision support
  • Requires at least 8‑k context for memory estimates
  • No mixture of experts

Best for

  • Chat applications needing long context
  • Fine‑tuning on custom datasets
  • Research on sparsity‑aware models

Who it’s for. Developers and researchers who need a large‑parameter model with a 32768‑token context window and an apache‑2.0 license. The model is suitable for environments where memory constraints can be managed with the provided quantizations.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.6 GB
Fits Get file →
IQ1_S3.6 GB 5.2 GB
Fits Get file →
IQ1_M4.0 GB 5.5 GB
Fits Get file →
IQ2_XXS4.5 GB 6.0 GB
Fits Get file →
IQ2_XS4.9 GB 6.5 GB
Fits Get file →
IQ2_S5.1 GB 6.7 GB
Fits Get file →
IQ2_M5.5 GB 7.1 GB
Fits Get file →
Q2_K_S5.6 GB 7.2 GB
Fits Get file →
Q2_K6.0 GB 7.6 GB
Tight Get file →
IQ3_XXS6.2 GB 7.8 GB
Tight Get file →
IQ3_XS6.7 GB 8.2 GB
Too big Get file →
Q3_K_S7.0 GB 8.5 GB
Too big Get file →
IQ3_S7.0 GB 8.6 GB
Too big Get file →
IQ3_M7.2 GB 8.7 GB
Too big Get file →
Q3_K_M7.7 GB 9.3 GB
Too big Get file →
Q3_K_L8.3 GB 9.8 GB
Too big Get file →
IQ4_XS8.5 GB 10.1 GB
Too big Get file →
IQ4_NL9.0 GB 10.6 GB
Too big Get file →
Q4_09.0 GB 10.6 GB
Too big Get file →
Q4_K_S9.0 GB 10.6 GB
Too big Get file →
Q4_K_M9.5 GB 11.1 GB
Too big Get file →
Q4_19.9 GB 11.5 GB
Too big Get file →
Q5_K_S10.8 GB 12.4 GB
Too big Get file →
Q5_K_M11.1 GB 12.7 GB
Too big Get file →
Q6_K12.8 GB 14.4 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_S (3.65 GB, 5.2 GB memory at 8k context) or Q2_K (5.99 GB, 7.6 GB memory). For 16‑GB VRAM, Q4_K_M (9.52 GB, 11.1 GB memory) or Q5_K_M (11.11 GB, 12.7 GB memory) are suitable. Larger VRAM allows Q6_K (12.81 GB, 14.4 GB memory).

What GPU do you need for KafkaLM 15B?

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 quant should you choose?

Q4_K_M is the usual starting point for KafkaLM 15B: 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

Architecturellama
Parameters15.6B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bymradermacher
FamilyKafkalm
Licenseapache-2.0
Downloads (HF)665
Last updated2025-12-23

Frequently asked questions about KafkaLM 15B

How much VRAM does KafkaLM 15B 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 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 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 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 GGUF?

The files are on Hugging Face in the mradermacher/KafkaLM-15B-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 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 on 8 GB VRAM?

Yes, with IQ1_S or Q2_K quantizations, which fit within 8‑GB VRAM and use about 5–7 GB memory at 8k context.

Does KafkaLM 15B support vision tasks?

No, the model has no vision capabilities.

What license applies to KafkaLM 15B?

The model is released under the apache‑2.0 license.

Other GGUFs of KafkaLM-15B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kafkalm models

All Kafkalm →

Other medium models

All medium models →