QW

Qwen2.5 Coder 3B Instruct Heretic

QwenGGUF by mradermacherUpdated 2026-09-16
Download on Hugging Face
Parameters3.09B
Context32K
Layers36
Architectureqwen2
Smallest quant1.3 GB
Quick answer

Qwen2.5 Coder 3B Instruct Heretic needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 1.3 GB (Q2_K) to 6.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Qwen2.5 Coder 3B Instruct Heretic – uncensored code model

Qwen2.5 Coder 3B Instruct Heretic is a 3.09 B parameter model focused on coding and roleplay. It removes refusal guardrails from the base Qwen2.5-Coder-3B-Instruct model, enabling direct code generation. The model runs natively in llama.cpp, Ollama, LM Studio, Jan, vLLM, and SGLang.

Good at

  • Coding tasks
  • Direct code generation
  • Roleplay

Limits

  • No safety filtering
  • No vision support
  • Requires 8 k context for estimates

Best for

  • Local coding assistants
  • Copilot‑style help
  • Code generation on consumer CPUs

Who it’s for. Developers who need a 3B code‑focused model without refusal guardrails for local deployment. Suitable for small machines and consumer CPUs via GGUF.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.3 GB 2.1 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
IQ4_XS1.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →
Q8_03.3 GB 4.1 GB
Fits Get file →
F166.2 GB 7.0 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (est. 2.7 GB) or Q5_K_S (est. 3 GB). If 12 GB VRAM is available, Q6_K (est. 3.3 GB) or Q8_0 (est. 4.1 GB) provide higher quality. F16 requires 7 GB and is best for maximum fidelity.

What GPU do you need for Qwen2.5 Coder 3B Instruct 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 Q6_K (2.5 GB file, about 3.3 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.3 GB file, about 4.1 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (6.2 GB file, about 7.0 GB in use).

Which Qwen2.5 Coder 3B Instruct Heretic quant should you choose?

Q4_K_M is the usual starting point for Qwen2.5 Coder 3B Instruct Heretic: it balances file size and quality well. Here it is a 1.9 GB file.

The Q8_0 file is 3.3 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 1.3 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

Architectureqwen2
Parameters3.09B
Layers36
Trained context32,768 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyQwen
Licenseother
Downloads (HF)1,106
Last updated2026-09-16

Frequently asked questions about Qwen2.5 Coder 3B Instruct Heretic

How much VRAM does Qwen2.5 Coder 3B Instruct Heretic need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 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 Qwen2.5 Coder 3B Instruct Heretic on an 8 GB GPU?

Yes, with F16: the 6.2 GB file needs about 7.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen2.5 Coder 3B Instruct Heretic GGUF?

It depends on the quant: Q2_K is 1.3 GB, Q3_K_S is 1.5 GB, Q3_K_M is 1.6 GB, Q3_K_L is 1.7 GB, IQ4_XS is 1.8 GB, Q4_K_S is 1.8 GB and 6 more.

What context length does Qwen2.5 Coder 3B Instruct 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 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download Qwen2.5 Coder 3B Instruct Heretic GGUF?

The files are on Hugging Face in the mradermacher/Qwen2.5-Coder-3B-Instruct-heretic-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 Qwen2.5 Coder 3B Instruct Heretic use?

Hugging Face lists the license as other. 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 Qwen2.5 Coder 3B Instruct Heretic on 8 GB VRAM?

Yes, use Q4_K_M or Q5_K_S quantizations; they estimate 2.7 GB and 3 GB memory at 8 k context.

Does this model support vision tasks?

No, the model has no vision capability.

Is there any safety filtering on this model?

No safety filtering is applied; the refusal guardrails are removed.

Other GGUFs of Qwen2.5-Coder-3B-Instruct-heretic

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other tiny models

All tiny models →