CO

VL 1 Coder Heretic

CoderGGUF by haffnerUpdated 2026-06-11
Download on Hugging Face
Parameters7.62B
Context32K
Layers28
Architectureqwen2
Smallest quant1.4 GB
Quick answer

VL 1 Coder Heretic needs about 5.2 GB of memory at IQ4_XS (a 4.3 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 19 quants, from 1.4 GB (Q1_0) to 15.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.

VL 1 Coder Heretic – 7.62B Qwen2 coding model with vision and tool use

VL 1 Coder Heretic is a 7.62‑billion parameter model based on Qwen2. It supports coding, reasoning, tools, and vision. The model is released under the apache‑2.0 license and offers a 32‑k token context window.

Good at

  • Coding production‑ready code
  • Reasoning with dense internal steps
  • Vision‑enabled code generation

Limits

  • No vision support on low‑VRAM devices
  • Requires 32‑k context for full capability
  • License is apache‑2.0

Best for

  • Developing complex software systems
  • Generating code from visual inputs
  • Automating coding tasks with tool calls

Who it’s for. Engineers and developers who need a large, multi‑modal coding assistant. The model is suitable for teams building production‑grade code and for individuals seeking advanced reasoning in code generation.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q1_01.4 GB 2.4 GB
Fits Get file →
TQ1_02.1 GB 3.1 GB
Fits Get file →
TQ2_02.4 GB 3.4 GB
Fits Get file →
Q2_K3.0 GB 4.0 GB
Fits Get file →
Q3_K_S3.5 GB 4.5 GB
Fits Get file →
IQ3_S3.5 GB 4.5 GB
Fits Get file →
IQ3_M3.6 GB 4.5 GB
Fits Get file →
Q3_K_M3.8 GB 4.8 GB
Fits Get file →
Q3_K_L4.1 GB 5.1 GB
Fits Get file →
IQ4_XS4.3 GB 5.2 GB
Fits Get file →
IQ4_NL4.5 GB 5.4 GB
Fits Get file →
Q4_14.9 GB 5.8 GB
Fits Get file →
Q5_05.3 GB 6.3 GB
Fits Get file →
Q5_K_S5.3 GB 6.3 GB
Fits Get file →
Q5_K_M5.4 GB 6.4 GB
Fits Get file →
Q5_15.8 GB 6.7 GB
Fits Get file →
Q6_K6.3 GB 7.2 GB
Tight Get file →
Q8_08.1 GB 9.1 GB
Too big Get file →
BF1615.2 GB 16.2 GB
Too big Get file →

For 8‑GB VRAM, use Q4_1 (5.8 GB memory estimate). For 12‑GB VRAM, Q5_0 (6.3 GB estimate) or Q5_K_S (6.3 GB). For 16‑GB VRAM, Q6_K (7.2 GB estimate) provides higher quality. Memory estimates are approximate.

What GPU do you need for VL 1 Coder Heretic?

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 Q2_K (3.0 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).

Which VL 1 Coder Heretic quant should you choose?

IQ4_XS (4.3 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q1_0 at 1.4 GB, with the quality trade-offs that come with fewer bits. Lower bit counts mean smaller files and more quality loss.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters7.62B
Layers28
Trained context32,768 tokens
KV cache (fp16)56 KB per token

Source

Quantized byhaffner
FamilyCoder
Licenseapache-2.0
Downloads (HF)1,149
Last updated2026-06-11

Frequently asked questions about VL 1 Coder Heretic

How much VRAM does VL 1 Coder Heretic need?

About 5.2 GB at IQ4_XS with an 8K context window. That is the 4.3 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 VL 1 Coder Heretic on an 8 GB GPU?

Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of VL 1 Coder Heretic GGUF?

It depends on the quant: Q1_0 is 1.4 GB, TQ1_0 is 2.1 GB, TQ2_0 is 2.4 GB, Q2_K is 3.0 GB, Q3_K_S is 3.5 GB, IQ3_S is 3.5 GB and 13 more.

What context length does VL 1 Coder Heretic support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.

Where can I download VL 1 Coder Heretic GGUF?

The files are on Hugging Face in the haffner/VL-1-Coder-Heretic repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does VL 1 Coder Heretic 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 VL 1 Coder Heretic on 8 GB VRAM?

Yes, the Q4_1 quant uses about 5.8 GB of VRAM at 8k context, which fits within 8 GB.

Does the model support vision?

Yes, the model has vision capability, but it requires sufficient VRAM and a compatible backend.

What license does the model use?

The model is released under the apache‑2.0 license.

Other GGUFs of VL-1-Coder

Similar models

Browse all →

More from haffner

All by haffner →

More Coder models

All Coder →

Other small models

All small models →