AG

Agent A1 Alchemist Bf16

AgentGGUF by angelgalviscUpdated 2026-08-06
Download on Hugging Face
Parameters4.21B
Context256K
Layers32
Architectureqwen35
Smallest quant2.9 GB
Quick answer

Agent A1 Alchemist Bf16 needs about 4.5 GB of memory at Q4_1 (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

Agent A1 Alchemist Bf16 is a 4.21B-parameter Agent model in GGUF format, quantized by angelgalvisc. Its trained context length is 256K tokens. The repository has 1 quant file, from 2.9 GB (Q4_1) to 2.9 GB (Q4_1).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_12.9 GB 4.5 GB
Fits Get file →

What GPU do you need for Agent A1 Alchemist Bf16?

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: the best quant that fits is Q4_1 (2.9 GB file, about 4.5 GB in use).

Which Agent A1 Alchemist Bf16 quant should you choose?

Q4_1 (2.9 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters4.21B
Layers32
Trained context262,144 tokens
KV cache (fp16)128 KB per token

Source

Quantized byangelgalvisc
FamilyAgent
Licenseapache-2.0
Downloads (HF)44
Last updated2026-08-06

Frequently asked questions about Agent A1 Alchemist Bf16

How much VRAM does Agent A1 Alchemist Bf16 need?

About 4.5 GB at Q4_1 with an 8K context window. That is the 2.9 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 Agent A1 Alchemist Bf16 on an 8 GB GPU?

Yes, with Q4_1: the 2.9 GB file needs about 4.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Agent A1 Alchemist Bf16 GGUF?

It depends on the quant: Q4_1 is 2.9 GB.

What context length does Agent A1 Alchemist Bf16 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download Agent A1 Alchemist Bf16 GGUF?

The files are on Hugging Face in the angelgalvisc/agent-a1-alchemist-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 Agent A1 Alchemist Bf16 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.

Similar models

Browse all →

More Agent models

All Agent →

Other small models

All small models →