SAGE MM Qwen3 VL 4B SFT needs about 4.4 GB of memory at Q4_K_M (a 2.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 37 quants, from 0.0 GB to 8.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
4.41B‑parameter vision‑language model for long‑video reasoning
SAGE‑MM Qwen3 VL 4B SFT is a 4.41‑billion‑parameter model fine‑tuned from Qwen3‑VL‑4B‑Instruct. It processes video frames and metadata to decide whether a query can be answered immediately or requires tool usage. The model outputs JSON actions for specialized tools such as web‑search, transcribe‑speech, and visual analysis.
Good at
- Video Q&A with tool orchestration
- Vision‑language reasoning
- JSON‑action generation
Limits
- No native vision support without SAGE runtime
- Requires 8‑k context for estimates
- Apache‑2.0 license limits commercial use
Best for
- Long‑form video analysis
- Tool‑driven question answering
- Research prototyping
Who it’s for. Researchers and developers building video‑centric agents who need a lightweight vision‑language backbone. The model is intended for research and educational use under the Apache‑2.0 license and requires the SAGE GitHub runtime for tool execution.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.7 GB | Fits | Get file → | |
| IQ1_S | 1.2 GB | 2.9 GB | Fits | Get file → | |
| IQ1_M | 1.3 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XXS | 1.4 GB | 3.1 GB | Fits | Get file → | |
| IQ2_XS | 1.5 GB | 3.2 GB | Fits | Get file → | |
| IQ2_S | 1.6 GB | 3.3 GB | Fits | Get file → | |
| IQ2_M | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q2_K_S | 1.7 GB | 3.4 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 3.5 GB | Fits | Get file → | |
| Q2_K | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XXS | 1.8 GB | 3.5 GB | Fits | Get file → | |
| IQ3_XS | 2.0 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ3_S | 2.1 GB | 3.8 GB | Fits | Get file → | |
| IQ3_M | 2.1 GB | 3.8 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_M | 2.2 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.1 GB | Fits | Get file → | |
| Q3_K_L | 2.4 GB | 4.1 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.2 GB | Fits | Get file → | |
| IQ4_XS | 2.5 GB | 4.2 GB | Fits | Get file → | |
| Q4_0 | 2.6 GB | 4.3 GB | Fits | Get file → | |
| IQ4_NL | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_S | 2.6 GB | 4.3 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q4_K_M | 2.7 GB | 4.4 GB | Fits | Get file → | |
| Q4_1 | 2.8 GB | 4.5 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_S | 3.1 GB | 4.8 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q5_K_M | 3.2 GB | 4.9 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q6_K | 3.6 GB | 5.3 GB | Fits | Get file → | |
| Q8_0 | 4.7 GB | 6.4 GB | Fits | Get file → | |
| F16 | 8.8 GB | 10.5 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ2_XXS (1.37 GB, 3.1 GB memory) or Q2_K (1.8 GB, 3.5 GB memory). For 12‑GB VRAM, IQ4_XS (2.48 GB, 4.2 GB memory) or Q4_K_M (2.72 GB, 4.4 GB memory) are suitable. Larger VRAM allows Q6_K (3.63 GB, 5.3 GB memory) or Q8_0 (4.69 GB, 6.4 GB memory).
What GPU do you need for SAGE MM Qwen3 VL 4B SFT?
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 Q3_K_M (2.2 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (3.6 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.7 GB file, about 6.4 GB in use).
- 12 GB VRAM: the best quant that fits is F16 (8.8 GB file, about 10.5 GB in use).
Which SAGE MM Qwen3 VL 4B SFT quant should you choose?
Q4_K_M is the usual starting point for SAGE MM Qwen3 VL 4B SFT: it balances file size and quality well. Here it is a 2.7 GB file.
The Q8_0 file is 4.7 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 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 SAGE MM Qwen3 VL 4B SFT
How much VRAM does SAGE MM Qwen3 VL 4B SFT need?
About 4.4 GB at Q4_K_M with an 8K context window. That is the 2.7 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 SAGE MM Qwen3 VL 4B SFT on an 8 GB GPU?
Yes, with Q8_0: the 4.7 GB file needs about 6.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SAGE MM Qwen3 VL 4B SFT GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.2 GB, IQ1_M is 1.3 GB, IQ2_XXS is 1.4 GB, IQ2_XS is 1.5 GB, IQ2_S is 1.6 GB and 31 more.
What context length does SAGE MM Qwen3 VL 4B SFT 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 4.8 GB at 32K.
Where can I download SAGE MM Qwen3 VL 4B SFT GGUF?
The files are on Hugging Face in the prithivMLmods/SAGE-MM-Qwen3-VL-4B-SFT-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 SAGE MM Qwen3 VL 4B SFT 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, use a quant such as IQ2_XXS or Q2_K, which estimate 3.1–3.5 GB memory at 8‑k context.
Does the model support image input directly?
It requires the SAGE runtime to parse frames and metadata; it does not process raw images alone.
Is the model licensed for commercial use?
It is licensed under Apache‑2.0, intended for research and educational use; commercial use requires compliance with the license.