Knight School Qwen3.5 2b Primer M needs about 2.2 GB of memory at Q4_K_M (a 1.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.0 GB (Q2_K) to 3.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
Knight School Qwen3.5 2b Primer M – a chess‑focused LLM
Knight School Qwen3.5 2b Primer M is a 1.88B‑parameter model fine‑tuned on chess puzzles. It supports reasoning, tools and vision. The model is released under Apache‑2.0 and can be used with GGUF quantizations.
Good at
- Chess puzzle solving
- Board reading
- Legal move generation
Limits
- Large context size 262144 tokens
- Requires at least 1.9 GB VRAM for Q2_K
- No external LLM‑generated data in training
Best for
- Chess training apps
- Puzzle generation tools
- Educational chess assistants
Who it’s for. Developers building chess‑centric applications or researchers needing a lightweight chess LLM. The model is ideal for environments with limited GPU memory but sufficient VRAM for the chosen quant.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.0 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_M | 1.1 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_L | 1.2 GB | 2.1 GB | Fits | Get file → | |
| IQ4_XS | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_S | 1.2 GB | 2.1 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → | |
| Q5_K_S | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.6 GB | 2.5 GB | Fits | Get file → | |
| Q8_0 | 2.0 GB | 2.9 GB | Fits | Get file → | |
| F16 | 3.8 GB | 4.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 2.2 GB) or Q5_K_M (est. 2.3 GB). For 4 GB VRAM, Q3_K_M (est. 2 GB) or Q3_K_S (est. 1.9 GB) are suitable. Higher precision quants like F16 require 4.7 GB VRAM and are best on 8 GB+ setups.
What GPU do you need for Knight School Qwen3.5 2b Primer M?
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 Q8_0 (2.0 GB file, about 2.9 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.8 GB file, about 4.7 GB in use).
Which Knight School Qwen3.5 2b Primer M quant should you choose?
Q4_K_M is the usual starting point for Knight School Qwen3.5 2b Primer M: it balances file size and quality well. Here it is a 1.3 GB file.
The Q8_0 file is 2.0 GB, about 1.6 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 1.0 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 Knight School Qwen3.5 2b Primer M
How much VRAM does Knight School Qwen3.5 2b Primer M need?
About 2.2 GB at Q4_K_M with an 8K context window. That is the 1.3 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 Knight School Qwen3.5 2b Primer M on an 8 GB GPU?
Yes, with F16: the 3.8 GB file needs about 4.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Knight School Qwen3.5 2b Primer M GGUF?
It depends on the quant: Q2_K is 1.0 GB, Q3_K_S is 1.0 GB, Q3_K_M is 1.1 GB, Q3_K_L is 1.2 GB, IQ4_XS is 1.2 GB, Q4_K_S is 1.2 GB and 6 more.
What context length does Knight School Qwen3.5 2b Primer M support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.7 GB at 32K.
Where can I download Knight School Qwen3.5 2b Primer M GGUF?
The files are on Hugging Face in the mradermacher/knight-school-qwen3.5-2b-primer-m-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 Knight School Qwen3.5 2b Primer M 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 this model on 8 GB VRAM?
Yes, quantizations such as Q4_K_M or Q5_K_M use about 2.2–2.3 GB VRAM at 8 k context, leaving headroom for other processes.
Does the model support vision tasks?
Yes, the model has detected vision ability, but no external vision datasets were used in training.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.