GP

Codegpt Oss 20b

gpt-ossGGUF by mradermacherUpdated 2025-12-04
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.0 GB
Quick answer

Codegpt Oss 20b needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.0 GB to 22.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Codegpt Oss 20b – LoRA‑tuned for competitive programming

Codegpt Oss 20b is a 20.9B‑parameter model fine‑tuned with LoRA for competitive programming in Python. It generates chain‑of‑thought reasoning traces in English or Ukrainian and supports up to 32k context tokens.

Good at

  • Python competitive programming
  • Chain‑of‑thought reasoning
  • Tool usage

Limits

  • Only tuned for Python coding
  • Requires CC BY 4.0 attribution
  • Training data small, may overfit

Best for

  • Solving Codeforces problems
  • Generating detailed Python solutions
  • Debugging code with reasoning

Who it’s for. Developers and competitive programmers who need detailed reasoning and explanations in Python. The model is ideal for educational use and debugging tasks where chain‑of‑thought is valuable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.9 GB
Fits Get file →
IQ1_M12.0 GB 12.9 GB
Too big Get file →
IQ1_S12.0 GB 12.9 GB
Too big Get file →
IQ2_XXS12.0 GB 12.9 GB
Too big Get file →
IQ2_XS12.0 GB 12.9 GB
Too big Get file →
Q3_K_S12.1 GB 13.0 GB
Too big Get file →
IQ2_M12.1 GB 13.0 GB
Too big Get file →
IQ2_S12.1 GB 13.0 GB
Too big Get file →
IQ3_S12.1 GB 13.0 GB
Too big Get file →
IQ3_XS12.1 GB 13.0 GB
Too big Get file →
IQ3_XXS12.1 GB 13.0 GB
Too big Get file →
Q2_K12.1 GB 13.0 GB
Too big Get file →
IQ4_XS12.1 GB 13.0 GB
Too big Get file →
Q2_K_S12.1 GB 13.0 GB
Too big Get file →
Q4_012.1 GB 13.1 GB
Too big Get file →
IQ3_M12.2 GB 13.1 GB
Too big Get file →
Q3_K_M12.9 GB 13.8 GB
Too big Get file →
Q3_K_L13.3 GB 14.2 GB
Too big Get file →
Q4_113.4 GB 14.3 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q4_K_M15.8 GB 16.7 GB
Too big Get file →
Q5_K_S15.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →

For 8‑GB VRAM, use IQ1_M (12.02 GB, 12.9 GB memory at 8k context). For 16‑GB VRAM, Q4_K_M (15.81 GB, 16.7 GB memory) offers a good balance. For 24‑GB VRAM, Q6_K (22.19 GB, 23.1 GB memory) provides the highest quality.

What GPU do you need for Codegpt Oss 20b?

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 the main file (0.0 GB file, about 0.9 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_S (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 23.1 GB in use).

Which Codegpt Oss 20b quant should you choose?

Q4_K_M is the usual starting point for Codegpt Oss 20b: it balances file size and quality well. Here it is a 15.8 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

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bymradermacher
Familygpt-oss
Licensecc-by-4.0
Downloads (HF)966
Last updated2025-12-04

Frequently asked questions about Codegpt Oss 20b

How much VRAM does Codegpt Oss 20b need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 Codegpt Oss 20b on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Codegpt Oss 20b GGUF?

It depends on the quant: file is 0.0 GB, IQ1_M is 12.0 GB, IQ1_S is 12.0 GB, IQ2_XXS is 12.0 GB, IQ2_XS is 12.0 GB, Q3_K_S is 12.1 GB and 18 more.

What context length does Codegpt Oss 20b support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Codegpt Oss 20b GGUF?

The files are on Hugging Face in the mradermacher/codegpt-oss-20b-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 Codegpt Oss 20b use?

Hugging Face lists the license as cc-by-4.0. 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 Codegpt Oss 20b on 8 GB VRAM?

Yes, using the IQ1_M quant (12.02 GB file, ~12.9 GB memory at 8k context).

Does the model support vision or image input?

No, it only processes text and is tuned for Python code.

What license does the model use?

CC BY 4.0; attribution is required when sharing or using the model.

Other GGUFs of codegpt-oss-20b

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →