CO

context 1

ContextGGUF by nicolasembletonUpdated 2026-03-28
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.0 GB
Quick answer

context 1 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 37 quants, from 12.0 GB (IQ1_M) to 41.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

20.9B parameter Mixture‑of‑Experts search model

Context‑1 is a 20.9B parameter MoE causal language model designed for retrieval and query decomposition. It is trained to iteratively search a corpus, edit its own context, and call tools. The model is released under Apache‑2.0.

Good at

  • Query decomposition
  • Parallel tool calling
  • Self‑editing context

Limits

  • Requires an agent harness
  • No vision support
  • Large VRAM needed for high‑quality quantizations

Best for

  • Retrieval‑augmented agents
  • Complex multi‑hop query handling
  • Tool‑enabled workflows

Who it’s for. Developers building retrieval subagents for LLMs. The model is intended for use within a dedicated agent harness that manages tool execution and context pruning.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
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 →
Q2_K_L12.1 GB 13.0 GB
Too big Get file →
TQ1_012.1 GB 13.0 GB
Too big Get file →
TQ2_012.1 GB 13.0 GB
Too big Get file →
IQ4_XS12.1 GB 13.0 GB
Too big Get file →
IQ4_NL12.1 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 →
Q2_K_XL12.6 GB 13.5 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 →
Q3_K_XL13.5 GB 14.4 GB
Too big Get file →
Q4_K_S14.7 GB 15.6 GB
Too big Get file →
Q5_014.7 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_115.9 GB 16.8 GB
Too big Get file →
Q4_K_XL16.3 GB 17.3 GB
Too big Get file →
Q5_K_M16.9 GB 17.8 GB
Too big Get file →
Q5_K_XL17.4 GB 18.3 GB
Too big Get file →
Q6_K22.2 GB 23.1 GB
Too big Get file →
Q8_022.3 GB 23.2 GB
Too big Get file →
Q6_K_XL22.7 GB 23.6 GB
Too big Get file →
Q8_022.8 GB 23.7 GB
Too big Get file →
BF1641.9 GB 42.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_M or IQ1_S (file size 12.02 GB, estimated memory 12.9 GB). For 12 GB VRAM, IQ2_XS (12.03 GB, 12.9 GB) or Q3_K_S (12.06 GB, 13 GB). For 16 GB VRAM, Q4_0 (12.15 GB, 13.1 GB) or Q4_K_S (14.65 GB, 15.6 GB).

What GPU do you need for context 1?

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: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q5_0 (14.7 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (22.8 GB file, about 23.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (22.8 GB file, about 23.7 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (41.9 GB file, about 42.8 GB in use).

Which context 1 quant should you choose?

Q4_K_M is the usual starting point for context 1: it balances file size and quality well. Here it is a 15.8 GB file.

The Q8_0 file is 22.3 GB, about 1.4 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 IQ1_M at 12.0 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

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

Source

Quantized bynicolasembleton
FamilyContext
Licenseapache-2.0
Downloads (HF)761
Last updated2026-03-28

Frequently asked questions about context 1

How much VRAM does context 1 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 context 1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of context 1 GGUF?

It depends on the quant: 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, IQ2_M is 12.1 GB and 31 more.

What context length does context 1 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 context 1 GGUF?

The files are on Hugging Face in the nicolasembleton/context-1-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 context 1 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 Context‑1 on 8 GB VRAM?

Use IQ1_M or IQ1_S quantizations; they require about 12.9 GB of VRAM at 8 k context.

Does Context‑1 support vision?

No, the model has no vision capability.

What license applies to Context‑1?

The model is released under the Apache‑2.0 license.

Other GGUFs of context-1

Similar models

Browse all →

More from nicolasembleton

All by nicolasembleton →

More Context models

All Context →

Other medium models

All medium models →