AF

AFM 4.5B

AfmGGUF by arcee-aiUpdated 2025-09-17
Download on Hugging Face
Parameters4.62B
Context64K
Layers36
Architecturearcee
Smallest quant1.7 GB
Quick answer

AFM 4.5B needs about 4.0 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 24 quants, from 1.7 GB (IQ2_M) to 9.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.

AFM 4.5B – 4.5 B parameter instruction‑tuned model

AFM 4.5B is a 4.5 B parameter instruction‑tuned model from Arcee.ai. It is trained on 8 T tokens with a focus on mathematical reasoning and code generation. The model is released under Apache 2.0 and supports deployment from cloud to edge.

Good at

  • Instruction following
  • Math reasoning
  • Code generation

Limits

  • No vision support
  • Requires 8 k context for estimates
  • Large VRAM for higher quants

Best for

  • Enterprise chatbots
  • Developer assistants
  • Educational tutoring

Who it’s for. Engineers and data scientists who need a reliable, instruction‑tuned model for text‑only applications. The model is suitable for both cloud and edge deployments where license compliance is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M1.7 GB 2.8 GB
Fits Get file →
Q2_K1.9 GB 3.0 GB
Fits Get file →
IQ3_XXS1.9 GB 3.0 GB
Fits Get file →
IQ3_XS2.1 GB 3.2 GB
Fits Get file →
Q3_K_S2.1 GB 3.2 GB
Fits Get file →
IQ3_M2.2 GB 3.3 GB
Fits Get file →
Q2_K_L2.2 GB 3.3 GB
Fits Get file →
Q3_K_M2.4 GB 3.5 GB
Fits Get file →
IQ4_XS2.6 GB 3.7 GB
Fits Get file →
Q3_K_L2.6 GB 3.7 GB
Fits Get file →
IQ4_NL2.7 GB 3.8 GB
Fits Get file →
Q4_02.7 GB 3.8 GB
Fits Get file →
Q4_K_S2.7 GB 3.8 GB
Fits Get file →
Q4_K_M2.9 GB 4.0 GB
Fits Get file →
Q3_K_XL2.9 GB 4.0 GB
Fits Get file →
Q4_13.0 GB 4.1 GB
Fits Get file →
Q4_K_L3.2 GB 4.3 GB
Fits Get file →
Q5_K_S3.2 GB 4.3 GB
Fits Get file →
Q5_K_M3.3 GB 4.4 GB
Fits Get file →
Q5_K_L3.5 GB 4.6 GB
Fits Get file →
Q6_K3.8 GB 4.9 GB
Fits Get file →
Q6_K_L4.0 GB 5.1 GB
Fits Get file →
Q8_04.9 GB 6.0 GB
Fits Get file →
BF169.2 GB 10.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_K_S (file size 2.7 GB, ~3.8 GB memory). For 12 GB VRAM, Q5_K_M or Q5_K_L (3.34 GB or 3.55 GB, ~4.4 GB or 4.6 GB memory). For 16 GB VRAM, Q6_K or Q6_K_L (3.8 GB or 3.96 GB, ~4.9 GB or 5.1 GB memory). Estimates are approximate.

What GPU do you need for AFM 4.5B?

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 Q3_K_XL (2.9 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.9 GB file, about 6.0 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (9.2 GB file, about 10.4 GB in use).

Which AFM 4.5B quant should you choose?

Q4_K_M is the usual starting point for AFM 4.5B: it balances file size and quality well. Here it is a 2.9 GB file.

The Q8_0 file is 4.9 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 IQ2_M at 1.7 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

Architecturearcee
Parameters4.62B
Layers36
Trained context65,536 tokens
KV cache (fp16)72 KB per token

Source

Quantized byarcee-ai
FamilyAfm
Licenseapache-2.0
Downloads (HF)1,185
Last updated2025-09-17

Frequently asked questions about AFM 4.5B

How much VRAM does AFM 4.5B need?

About 4.0 GB at Q4_K_M 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 AFM 4.5B on an 8 GB GPU?

Yes, with Q8_0: the 4.9 GB file needs about 6.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of AFM 4.5B GGUF?

It depends on the quant: IQ2_M is 1.7 GB, Q2_K is 1.9 GB, IQ3_XXS is 1.9 GB, IQ3_XS is 2.1 GB, Q3_K_S is 2.1 GB, IQ3_M is 2.2 GB and 18 more.

What context length does AFM 4.5B support?

The GGUF header lists a trained context length of 65,536 tokens (64K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.

Where can I download AFM 4.5B GGUF?

The files are on Hugging Face in the arcee-ai/AFM-4.5B-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 AFM 4.5B 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 AFM 4.5B on 8 GB VRAM?

Yes, using Q4_0 or Q4_K_S quantization, which require about 3.8 GB of VRAM at 8 k context.

Does AFM 4.5B support vision tasks?

No, the model is text‑only and has no vision capabilities.

Other GGUFs of AFM-4.5B

Similar models

Browse all →

More from arcee-ai

All by arcee-ai →

More Afm models

All Afm →

Other small models

All small models →