QwenGram-2B REAL-15M + linear750 needs about 2.3 GB of memory at Q4_K_M (a 1.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 1.4 GB (Q4_K_M) to 4.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.7 GB.
QwenGram-2B REAL-15M + linear750 – a 2B parameter Qwen3.5 derivative
QwenGram-2B is a 1.96B parameter causal language model derived from Qwen3.5-2B. It includes a 15,000,064 reader token set and a linear750 arbiter for dynamic arbitration. The model is released under Apache‑2.0 and is available in several GGUF quantizations.
Good at
- Efficient inference with low‑precision quantization
- Fast prototyping and fine‑tuning
- Research on reader‑arbiter architectures
Limits
- No vision support – only language
- Requires external PLE sidecar
- Large VRAM needed for higher precision
Best for
- Fine‑tuning small language tasks
- Rapid prototyping of reader‑based models
- Research on dynamic arbitration
Who it’s for. Developers and researchers who need a lightweight Qwen3.5‑based model for language‑only tasks and who can supply the required PLE sidecar. The model is suitable for prototyping and task‑specific fine‑tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.4 GB | 2.3 GB | Fits | Get file → | |
| Q6_K | 1.7 GB | 2.6 GB | Fits | Get file → | |
| Q8_0 | 2.2 GB | 3.1 GB | Fits | Get file → | |
| BF16 | 4.0 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (file size 1.4 GB, estimated 2.3 GB memory). For 12 GB VRAM, Q6_K (1.69 GB, 2.6 GB memory) is suitable. For 16 GB VRAM or more, Q8_0 (2.16 GB, 3.1 GB memory) or BF16 (3.98 GB, 4.9 GB memory) can be used.
What GPU do you need for QwenGram-2B REAL-15M + linear750?
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 (2.2 GB file, about 3.1 GB in use).
- 6 GB VRAM: the best quant that fits is BF16 (4.0 GB file, about 4.9 GB in use).
Which QwenGram-2B REAL-15M + linear750 quant should you choose?
Q4_K_M is the usual starting point for QwenGram-2B REAL-15M + linear750: it balances file size and quality well. Here it is a 1.4 GB file.
The Q8_0 file is 2.2 GB, about 1.5 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about QwenGram-2B REAL-15M + linear750
How much VRAM does QwenGram-2B REAL-15M + linear750 need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.4 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 QwenGram-2B REAL-15M + linear750 on an 8 GB GPU?
Yes, with BF16: the 4.0 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of QwenGram-2B REAL-15M + linear750 GGUF?
It depends on the quant: Q4_K_M is 1.4 GB, Q6_K is 1.7 GB, Q8_0 is 2.2 GB, BF16 is 4.0 GB.
What context length does QwenGram-2B REAL-15M + linear750 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 QwenGram-2B REAL-15M + linear750 GGUF?
The files are on Hugging Face in the Ninnix96/Qwengram-2B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does QwenGram-2B REAL-15M + linear750 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 QwenGram-2B on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 2.3 GB VRAM at 8 k context, which fits within 8 GB.
Does the model support vision tasks?
No, QwenGram-2B is a language‑only model and does not include vision capabilities.
What external files are needed to run the model?
An external PLE sidecar (Ivan Fioravanti's Q4_1 PLE GGUF) is required for inference.