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 12 quants, from 3.4 GB (Q2_K) to 17.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Kiesel v2 – 8.79B Granite 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 tool‑calling. The model supports a 131072 token context window and is released under Apache‑2.0.
Good at
- Reasoning with chain‑of‑thought
- Tool‑calling and function invocation
- Long‑context processing up to 131072 tokens
Limits
- No vision support
- Requires large VRAM for higher quants
- No mixture‑of‑experts
Best for
- Complex math and logic tasks
- Multi‑step coding assistance
- Agentic workflows with tool usage
Who it’s for. Developers and researchers needing a reasoning‑capable LLM that can run locally. The model is suitable for applications that require step‑by‑step reasoning and tool integration without external APIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 3.4 GB | 5.3 GB | Fits | Get file → | |
| Q3_K_S | 3.9 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_M | 4.3 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_L | 4.7 GB | 6.5 GB | Fits | Get file → | |
| IQ4_XS | 4.9 GB | 6.7 GB | Fits | Get file → | |
| Q4_K_S | 5.1 GB | 6.9 GB | Fits | Get file → | |
| Q4_K_M | 5.3 GB | 7.2 GB | Fits | Get file → | |
| Q5_K_S | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_M | 6.3 GB | 8.1 GB | Too big | Get file → | |
| Q6_K | 7.2 GB | 9.1 GB | Too big | Get file → | |
| Q8_0 | 9.3 GB | 11.2 GB | Too big | Get file → | |
| F16 | 17.6 GB | 19.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.3 GB file, 7.2 GB memory at 8 k context). For 12 GB VRAM, Q5_K_M (6.25 GB file, 8.1 GB memory) is a good balance. For 16 GB VRAM, Q6_K (7.22 GB file, 9.1 GB memory) offers higher precision.
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q3_K_S (3.9 GB file, about 5.8 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 Q8_0 (9.3 GB file, about 11.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.3 GB file, about 11.2 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (17.6 GB file, about 19.4 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.
The Q8_0 file is 9.3 GB, about 1.7 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.
If memory is tight, the smallest file is Q2_K at 3.4 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
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: Q2_K is 3.4 GB, Q3_K_S is 3.9 GB, Q3_K_M is 4.3 GB, Q3_K_L is 4.7 GB, IQ4_XS is 4.9 GB, Q4_K_S is 5.1 GB and 6 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-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, the Q4_K_M quant uses about 7.2 GB memory at 8 k context, fitting within 8 GB VRAM.
Does Kiesel v2 support vision?
No, the model has no vision capabilities.