BananaQwen needs about 11.3 GB of memory at Q4_K_M (a 9.6 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 12.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.7 GB.
15.5B parameter Qwen35 model in GGUF format
BananaQwen is a 15.5B parameter model based on the qwen35 architecture. It is available in multiple quantizations for use with llama.cpp. The model supports a context length of 262144 tokens.
Good at
- Large context handling
- Versatile quant options
- LLM inference on local hardware
Limits
- No vision support indicated
- License not specified
- No mixture of experts
Best for
- Long‑form text generation
- Fine‑tuning on local datasets
- Research on quantization effects
Who it’s for. Developers and researchers who need a large‑parameter LLM that can be run locally with llama.cpp. The model is suitable for those exploring different quantization strategies to balance performance and memory usage.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 4.4 GB | 6.1 GB | Fits | Get file → | |
| IQ1_M | 4.7 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 5.1 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XS | 5.5 GB | 7.1 GB | Fits | Get file → | |
| IQ2_S | 5.7 GB | 7.3 GB | Tight | Get file → | |
| IQ2_M | 6.0 GB | 7.7 GB | Tight | Get file → | |
| Q2_K_S | 6.2 GB | 7.8 GB | Tight | Get file → | |
| Q2_K | 6.4 GB | 8.1 GB | Too big | Get file → | |
| IQ3_XXS | 6.6 GB | 8.3 GB | Too big | Get file → | |
| IQ3_XS | 7.1 GB | 8.8 GB | Too big | Get file → | |
| Q3_K_S | 7.2 GB | 8.8 GB | Too big | Get file → | |
| IQ3_S | 7.4 GB | 9.0 GB | Too big | Get file → | |
| IQ3_M | 7.4 GB | 9.1 GB | Too big | Get file → | |
| Q3_K_M | 7.8 GB | 9.5 GB | Too big | Get file → | |
| Q3_K_L | 8.4 GB | 10.1 GB | Too big | Get file → | |
| IQ4_XS | 8.8 GB | 10.5 GB | Too big | Get file → | |
| Q4_0 | 9.1 GB | 10.8 GB | Too big | Get file → | |
| Q4_K_S | 9.1 GB | 10.8 GB | Too big | Get file → | |
| IQ4_NL | 9.2 GB | 10.9 GB | Too big | Get file → | |
| Q4_K_M | 9.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_1 | 9.9 GB | 11.6 GB | Too big | Get file → | |
| Q5_K_S | 10.8 GB | 12.5 GB | Too big | Get file → | |
| Q5_K_M | 11.1 GB | 12.8 GB | Too big | Get file → | |
| Q6_K | 12.7 GB | 14.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (4.43 GB, 6.1 GB memory) or IQ1_M (4.69 GB, 6.4 GB memory). With 12 GB VRAM, Q4_K_M (9.62 GB, 11.3 GB memory) or Q5_K_S (10.84 GB, 12.5 GB memory) are suitable. Larger VRAM allows higher‑quality quants such as Q5_K_M or Q6_K.
What GPU do you need for BananaQwen?
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 1.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.7 GB in use).
- 8 GB VRAM: the best quant that fits is Q2_K_S (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 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.7 GB file, about 14.4 GB in use).
Which BananaQwen quant should you choose?
Q4_K_M is the usual starting point for BananaQwen: it balances file size and quality well. Here it is a 9.6 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
Source
Frequently asked questions about BananaQwen
How much VRAM does BananaQwen need?
About 11.3 GB at Q4_K_M with an 8K context window. That is the 9.6 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 BananaQwen on an 8 GB GPU?
Yes, with Q2_K_S: 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 BananaQwen GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 4.4 GB, IQ1_M is 4.7 GB, IQ2_XXS is 5.1 GB, IQ2_XS is 5.5 GB, IQ2_S is 5.7 GB and 19 more.
What context length does BananaQwen support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.7 GB at 32K.
Where can I download BananaQwen GGUF?
The files are on Hugging Face in the mradermacher/BananaQwen-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run BananaQwen on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which require about 6.1–6.4 GB of VRAM at 8k context.
Does BananaQwen support vision tasks?
No vision support is indicated in the provided information.
What is the maximum context length of BananaQwen?
The model supports up to 262144 tokens of context.