alist food text qwen35 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 5 quants, from 0.1 GB (F16) to 1.3 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
Qwen3.5-2B fine‑tuned for food‑diary nutrition extraction
This model is a 2 B‑parameter Qwen3.5 variant fine‑tuned with LoRA for extracting nutrition facts from food diary text. It supports vision input and outputs a JSON object with macro‑ and micronutrient data. The base model and adapter are licensed Apache 2.0.
Good at
- Vision‑enabled nutrition extraction
- JSON‑structured macro/micronutrient output
- Low‑parameter efficient inference
Limits
- No chat template support
- Requires raw‑text prompt only
- No other vision tasks beyond food‑diary
Best for
- On‑device nutrition tracking apps
- Automated food‑diary parsing
- Health data ingestion pipelines
Who it’s for. Developers building mobile or embedded nutrition apps that need on‑device inference. Researchers prototyping vision‑language models for food analysis may also use this adapter.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.1 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.1 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.1 GB | 1.0 GB | Fits | Get file → | |
| F16 | 0.1 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_M | 1.3 GB | 2.2 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (1.28 GB file, ~2.2 GB VRAM at 8 k context). For higher VRAM budgets, the F16 quant (0.09 GB file, ~1 GB VRAM) provides better precision. Memory estimates are approximate.
What GPU do you need for alist food text qwen35?
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 Q4_K_M (1.3 GB file, about 2.2 GB in use).
Which alist food text qwen35 quant should you choose?
Q4_K_M is the usual starting point for alist food text qwen35: it balances file size and quality well. Here it is a 1.3 GB file.
If memory is tight, the smallest file is F16 at 0.1 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about alist food text qwen35
How much VRAM does alist food text qwen35 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 alist food text qwen35 on an 8 GB GPU?
Yes, with Q4_K_M: the 1.3 GB file needs about 2.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of alist food text qwen35 GGUF?
It depends on the quant: F16 is 0.1 GB, F16 is 0.1 GB, F16 is 0.1 GB, F16 is 0.1 GB, Q4_K_M is 1.3 GB.
What context length does alist food text qwen35 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 1.6 GB at 32K.
Where can I download alist food text qwen35 GGUF?
The files are on Hugging Face in the NateRunsA-LIST/alist-food-text-qwen35 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does alist food text qwen35 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, the Q4_K_M quant uses about 2.2 GB VRAM at 8 k context, which fits within an 8 GB budget.
Does it support chat templates?
No, the model requires the exact raw‑text prompt specified in the adapter documentation.
What vision capabilities does it have?
It includes a vision encoder trained for food‑diary images, but it is not a general vision model.