QW

Qwen2 Vl 2b Abliterated

QwenGGUF by mradermacherUpdated 2026-10-02
Download on Hugging Face
Parameters1.54B
Context32K
Layers28
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Qwen2 Vl 2b Abliterated needs about 1.7 GB of memory at Q4_K_M (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 1.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Qwen2‑VL‑2B Abliterated – a 1.54B‑parameter vision‑LLM with reduced refusal behavior

Qwen2‑VL‑2B Abliterated is a 1.54B‑parameter model that retains image understanding, visual question answering, and OCR. It removes the built‑in refusal direction, allowing it to comply with requests that the base model would refuse. The model supports a 32,768‑token context window.

Good at

  • Vision‑text reasoning
  • Visual question answering
  • OCR

Limits

  • No image generation
  • Reduced refusal control may allow harmful content
  • Requires 1.2–2 GB VRAM for Q2‑S to Q6‑K

Best for

  • Image captioning
  • Visual QA in chat
  • OCR extraction

Who it’s for. Developers and researchers needing a lightweight vision‑LLM that can handle text and image inputs without the base model’s refusal safeguards. Suitable for applications where compliance with all content policies is not critical.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.7 GB
Fits Get file →
IQ1_S0.4 GB 1.2 GB
Fits Get file →
IQ1_M0.5 GB 1.2 GB
Fits Get file →
IQ2_XXS0.5 GB 1.2 GB
Fits Get file →
IQ2_XS0.6 GB 1.3 GB
Fits Get file →
IQ2_S0.6 GB 1.3 GB
Fits Get file →
IQ2_M0.6 GB 1.3 GB
Fits Get file →
Q2_K_S0.6 GB 1.4 GB
Fits Get file →
IQ3_XXS0.7 GB 1.4 GB
Fits Get file →
Q2_K0.7 GB 1.4 GB
Fits Get file →
IQ3_XS0.7 GB 1.5 GB
Fits Get file →
Q3_K_S0.8 GB 1.5 GB
Fits Get file →
IQ3_S0.8 GB 1.5 GB
Fits Get file →
IQ3_M0.8 GB 1.5 GB
Fits Get file →
Q3_K_M0.8 GB 1.6 GB
Fits Get file →
Q3_K_L0.9 GB 1.6 GB
Fits Get file →
IQ4_XS0.9 GB 1.6 GB
Fits Get file →
IQ4_NL0.9 GB 1.7 GB
Fits Get file →
Q4_00.9 GB 1.7 GB
Fits Get file →
Q4_K_S0.9 GB 1.7 GB
Fits Get file →
Q4_K_M1.0 GB 1.7 GB
Fits Get file →
Q4_11.0 GB 1.8 GB
Fits Get file →
Q5_K_S1.1 GB 1.8 GB
Fits Get file →
Q5_K_M1.1 GB 1.9 GB
Fits Get file →
Q6_K1.3 GB 2.0 GB
Fits Get file →

For 8 GB VRAM, use Q2‑S (0.56 GB) or Q3‑K_S (0.76 GB). For 12 GB VRAM, Q4‑K_M (0.99 GB) or Q5‑K_S (1.1 GB) offer a good balance of size and performance. For 16 GB VRAM, Q6‑K (1.27 GB) provides the highest quality.

What GPU do you need for Qwen2 Vl 2b Abliterated?

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 Q6_K (1.3 GB file, about 2.0 GB in use).

Which Qwen2 Vl 2b Abliterated quant should you choose?

Q4_K_M is the usual starting point for Qwen2 Vl 2b Abliterated: it balances file size and quality well. Here it is a 1.0 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

Architectureqwen2vl
Parameters1.54B
Layers28
Trained context32,768 tokens
KV cache (fp16)28 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseapache-2.0
Downloads (HF)177
Last updated2026-10-02

Frequently asked questions about Qwen2 Vl 2b Abliterated

How much VRAM does Qwen2 Vl 2b Abliterated need?

About 1.7 GB at Q4_K_M with an 8K context window. That is the 1.0 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 Qwen2 Vl 2b Abliterated on an 8 GB GPU?

Yes, with Q6_K: the 1.3 GB file needs about 2.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2 Vl 2b Abliterated GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.4 GB, IQ1_M is 0.5 GB, IQ2_XXS is 0.5 GB, IQ2_XS is 0.6 GB, IQ2_S is 0.6 GB and 19 more.

What context length does Qwen2 Vl 2b Abliterated support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.

Where can I download Qwen2 Vl 2b Abliterated GGUF?

The files are on Hugging Face in the mradermacher/qwen2-vl-2b-abliterated-i1-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 Qwen2 Vl 2b Abliterated 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 Qwen2‑VL‑2B Abliterated on 8 GB VRAM?

Yes, use a quant such as Q2‑S or Q3‑K_S, which require about 1.2–1.5 GB of VRAM at 8k context.

Does this model generate images?

No, it is an understanding‑only vision model and does not produce or edit images.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of qwen2-vl-2b-abliterated

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →