ME

MechVL 4B SFT

MechvlGGUF by mradermacherUpdated 2026-10-20
Download on Hugging Face
Parameters4.02B
Context256K
Layers36
Architectureqwen3vl
Smallest quant1.7 GB
Quick answer

MechVL 4B SFT needs about 4.2 GB of memory at Q4_K_M (a 2.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 1.7 GB (Q2_K) to 8.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

MechVL 4B SFT – a multimodal LLM for mechanical drawing understanding

MechVL 4B SFT is a 4.02 billion parameter model based on qwen3vl. It supports vision and tool use and was trained with full‑parameter SFT on the MechVQA dataset. The model is released under Apache‑2.0.

Good at

  • Vision‑enabled mechanical drawing analysis
  • Tool‑aware reasoning
  • Instruction following

Limits

  • No vision support beyond 8‑bit quant
  • Large context requires high VRAM
  • Requires Apache‑2.0 license compliance

Best for

  • Mechanical engineering QA
  • Drawing interpretation tasks
  • Tool‑integrated workflows

Who it’s for. Engineers and researchers needing a specialized multimodal model for mechanical drawings. The model is suitable for developers who can run GGUF files with llama.cpp or vLLM and who need tool‑aware reasoning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.7 GB 3.4 GB
Fits Get file →
Q3_K_S1.9 GB 3.6 GB
Fits Get file →
Q3_K_M2.1 GB 3.8 GB
Fits Get file →
Q3_K_L2.2 GB 3.9 GB
Fits Get file →
IQ4_XS2.3 GB 4.0 GB
Fits Get file →
Q4_K_S2.4 GB 4.1 GB
Fits Get file →
Q4_K_M2.5 GB 4.2 GB
Fits Get file →
Q5_K_S2.8 GB 4.5 GB
Fits Get file →
Q5_K_M2.9 GB 4.6 GB
Fits Get file →
Q6_K3.3 GB 5.0 GB
Fits Get file →
Q8_04.3 GB 6.0 GB
Fits Get file →
F168.1 GB 9.8 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (file size 2.5 GB, estimated 4.2 GB memory). For 12 GB VRAM, Q5_K_M (2.89 GB, 4.6 GB memory) or Q6_K (3.31 GB, 5 GB memory) are suitable. For 16 GB VRAM, Q8_0 (4.28 GB, 6 GB memory) or F16 (8.05 GB, 9.8 GB memory) can be used.

What GPU do you need for MechVL 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 IQ4_XS (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (8.1 GB file, about 9.8 GB in use).

Which MechVL 4B SFT quant should you choose?

Q4_K_M is the usual starting point for MechVL 4B SFT: it balances file size and quality well. Here it is a 2.5 GB file.

The Q8_0 file is 4.3 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 Q2_K at 1.7 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
Parameters4.02B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyMechvl
Licenseapache-2.0
Downloads (HF)756
Last updated2026-10-20

Frequently asked questions about MechVL 4B SFT

How much VRAM does MechVL 4B SFT need?

About 4.2 GB at Q4_K_M with an 8K context window. That is the 2.5 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 MechVL 4B SFT on an 8 GB GPU?

Yes, with Q8_0: the 4.3 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of MechVL 4B SFT GGUF?

It depends on the quant: Q2_K is 1.7 GB, Q3_K_S is 1.9 GB, Q3_K_M is 2.1 GB, Q3_K_L is 2.2 GB, IQ4_XS is 2.3 GB, Q4_K_S is 2.4 GB and 6 more.

What context length does MechVL 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 MechVL 4B SFT GGUF?

The files are on Hugging Face in the mradermacher/MechVL-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 MechVL 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 MechVL 4B SFT on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires approximately 4.2 GB VRAM at 8k context.

Does the model support vision tasks?

Yes, the model has vision capability and tool use as detected abilities.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Mechvl models

All Mechvl →

Other small models

All small models →