SC

Scalpel VL 1.7B

ScalpelGGUF by mradermacherUpdated 2026-09-01
Download on Hugging Face
Parameters1.37B
Context256K
Layers21
Architectureqwen3vl
Smallest quant0.6 GB
Quick answer

Scalpel VL 1.7B needs about 2.1 GB of memory at Q4_K_M (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.6 GB (Q2_K) to 2.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.8 GB.

Scalpel VL 1.7B – a pruned Qwen3VL vision‑language model

Scalpel VL 1.7B is a 1.7B parameter vision‑language model based on Qwen3VL. It supports tools and vision and was produced by a seven‑round pruning and recovery process. The model is released under the apache‑2.0 license.

Good at

  • Vision‑language instruction following
  • Tool usage
  • Multilingual text generation

Limits

  • Requires 8k context for memory estimates
  • No weighted or matrix quantizations available
  • Limited to GGUF format

Best for

  • Image captioning
  • Code generation with tool calls
  • Multilingual Q&A

Who it’s for. Developers building lightweight vision‑language applications who need a small, open‑source model. The model is suitable for local deployment with limited GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K0.6 GB 1.9 GB
Fits Get file →
Q3_K_S0.7 GB 1.9 GB
Fits Get file →
Q3_K_M0.8 GB 2.0 GB
Fits Get file →
Q3_K_L0.8 GB 2.0 GB
Fits Get file →
IQ4_XS0.8 GB 2.0 GB
Fits Get file →
Q4_K_S0.9 GB 2.1 GB
Fits Get file →
Q4_K_M0.9 GB 2.1 GB
Fits Get file →
Q5_K_S1.0 GB 2.2 GB
Fits Get file →
Q5_K_M1.0 GB 2.2 GB
Fits Get file →
Q6_K1.1 GB 2.3 GB
Fits Get file →
Q8_01.5 GB 2.7 GB
Fits Get file →
F162.7 GB 3.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (file size 0.89 GB, estimated 2.1 GB memory). For 4 GB VRAM, use Q3_K_M (0.77 GB, 2 GB memory). For 2 GB VRAM, use Q2_K (0.65 GB, 1.9 GB memory).

What GPU do you need for Scalpel VL 1.7B?

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 F16 (2.7 GB file, about 3.9 GB in use).

Which Scalpel VL 1.7B quant should you choose?

Q4_K_M is the usual starting point for Scalpel VL 1.7B: it balances file size and quality well. Here it is a 0.9 GB file.

The Q8_0 file is 1.5 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 0.6 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

Architectureqwen3vl
Parameters1.37B
Layers21
Trained context262,144 tokens
KV cache (fp16)84 KB per token

Source

Quantized bymradermacher
FamilyScalpel
Licenseapache-2.0
Downloads (HF)589
Last updated2026-09-01

Frequently asked questions about Scalpel VL 1.7B

How much VRAM does Scalpel VL 1.7B need?

About 2.1 GB at Q4_K_M with an 8K context window. That is the 0.9 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 Scalpel VL 1.7B on an 8 GB GPU?

Yes, with F16: the 2.7 GB file needs about 3.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Scalpel VL 1.7B GGUF?

It depends on the quant: Q2_K is 0.6 GB, Q3_K_S is 0.7 GB, Q3_K_M is 0.8 GB, Q3_K_L is 0.8 GB, IQ4_XS is 0.8 GB, Q4_K_S is 0.9 GB and 6 more.

What context length does Scalpel VL 1.7B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.8 GB at 32K.

Where can I download Scalpel VL 1.7B GGUF?

The files are on Hugging Face in the mradermacher/Scalpel-VL-1.7B-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 Scalpel VL 1.7B 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 Scalpel VL 1.7B on 8 GB VRAM?

Yes, the Q4_K_M quant requires about 2.1 GB memory at 8k context, well within 8 GB VRAM.

Does the model support vision tasks?

Yes, Scalpel VL 1.7B has vision capability as indicated in its detected abilities.

What license applies to this model?

The model is released under the apache‑2.0 license.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Scalpel models

All Scalpel →

Other tiny models

All tiny models →