GR

Kiesel v2

GraniteGGUF by mradermacherUpdated 2026-10-10
Download on Hugging Face
Parameters8.8B
Context128K
Layers40
Architecturegranite
Smallest quant0.0 GB
Quick answer

Kiesel v2 needs about 7.2 GB of memory at Q4_K_M (a 5.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Kiesel v2 – an 8.8B Granite‑4.2 model with built‑in reasoning

Kiesel v2 is a GGUF‑quantized version of IBM Granite‑4.2‑8B. It offers native chain‑of‑thought reasoning and flexible thinking modes. The model is licensed under Apache‑2.0 and supports a 131072‑token context window.

Good at

  • Native reasoning and chain‑of‑thought
  • Flexible thinking modes
  • Tool‑calling with reasoning

Limits

  • Large context window requires significant VRAM
  • No vision support
  • Requires Apache‑2.0 license compliance

Best for

  • Complex math and logic tasks
  • Multi‑step coding problems
  • Agentic tool‑calling workflows

Who it’s for. Developers and researchers needing a reasoning‑capable LLM that can be run locally with GGUF. The model is suitable for applications that benefit from step‑by‑step reasoning and tool integration.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ1_S2.1 GB 4.0 GB
Fits Get file →
IQ1_M2.3 GB 4.1 GB
Fits Get file →
IQ2_XXS2.5 GB 4.4 GB
Fits Get file →
IQ2_XS2.8 GB 4.6 GB
Fits Get file →
IQ2_S2.9 GB 4.8 GB
Fits Get file →
IQ2_M3.2 GB 5.0 GB
Fits Get file →
Q2_K_S3.2 GB 5.0 GB
Fits Get file →
Q2_K3.4 GB 5.3 GB
Fits Get file →
IQ3_XXS3.5 GB 5.4 GB
Fits Get file →
IQ3_XS3.8 GB 5.6 GB
Fits Get file →
Q3_K_S3.9 GB 5.8 GB
Fits Get file →
IQ3_S4.0 GB 5.8 GB
Fits Get file →
IQ3_M4.1 GB 5.9 GB
Fits Get file →
Q3_K_M4.3 GB 6.2 GB
Fits Get file →
Q3_K_L4.7 GB 6.5 GB
Fits Get file →
IQ4_XS4.8 GB 6.7 GB
Fits Get file →
Q4_05.1 GB 6.9 GB
Fits Get file →
IQ4_NL5.1 GB 6.9 GB
Fits Get file →
Q4_K_S5.1 GB 6.9 GB
Fits Get file →
Q4_K_M5.3 GB 7.2 GB
Fits Get file →
Q4_15.6 GB 7.4 GB
Tight Get file →
Q5_K_S6.1 GB 7.9 GB
Tight Get file →
Q5_K_M6.3 GB 8.1 GB
Too big Get file →
Q6_K7.2 GB 9.1 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S or IQ1_M (≈4 GB VRAM). For 12 GB VRAM, IQ2_S or Q2_K (≈5 GB). For 16 GB VRAM, Q3_K_M or Q4_K_M (≈6–7 GB). Larger quants need more VRAM.

What GPU do you need for Kiesel v2?

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 IQ1_S (2.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ3_M (4.1 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_S (6.1 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (7.2 GB file, about 9.1 GB in use).

Which Kiesel v2 quant should you choose?

Q4_K_M is the usual starting point for Kiesel v2: it balances file size and quality well. Here it is a 5.3 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

Architecturegranite
Parameters8.8B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyGranite
Licenseapache-2.0
Downloads (HF)4,171
Last updated2026-10-10

Frequently asked questions about Kiesel v2

How much VRAM does Kiesel v2 need?

About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.3 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 Kiesel v2 on an 8 GB GPU?

Yes, with Q5_K_S: the 6.1 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 Kiesel v2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.8 GB, IQ2_S is 2.9 GB and 19 more.

What context length does Kiesel v2 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Kiesel v2 GGUF?

The files are on Hugging Face in the mradermacher/kiesel-v2-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 Kiesel v2 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 Kiesel v2 on 8 GB VRAM?

Yes, with IQ1_S or IQ1_M quantization the model uses about 4 GB VRAM at 8k context.

Does Kiesel v2 support vision?

No, the model has no vision capabilities.

Other GGUFs of granite-4.2-8b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Granite models

All Granite →

Other small models

All small models →