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 25 quants, from 0.0 GB to 9.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
AFM‑4.5B, a 4.5B parameter instruction‑tuned model
AFM‑4.5B is a 4.5B parameter instruction‑tuned model from Arcee.ai. It is trained on 8T tokens with a focus on mathematical reasoning and code generation. The model is available in multiple GGUF quantizations.
Good at
- Instruction following
- Code generation
- Mathematical reasoning
Limits
- No vision support
- Requires 8k context for memory estimates
- Apache‑2.0 license
Best for
- Enterprise‑grade chatbots
- Code assistant tools
- Educational tutoring
Who it’s for. Developers and enterprises looking for a versatile instruction‑tuned model that can run on a range of hardware. The model is suitable for cloud and edge deployments where a 4.5B parameter size is acceptable.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.1 GB | Fits | Get file → | |
| IQ2_M | 1.7 GB | 2.8 GB | Fits | Get file → | |
| Q2_K | 1.9 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XXS | 1.9 GB | 3.0 GB | Fits | Get file → | |
| IQ3_XS | 2.1 GB | 3.2 GB | Fits | Get file → | |
| Q3_K_S | 2.1 GB | 3.2 GB | Fits | Get file → | |
| IQ3_M | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q2_K_L | 2.2 GB | 3.3 GB | Fits | Get file → | |
| Q3_K_M | 2.4 GB | 3.5 GB | Fits | Get file → | |
| IQ4_XS | 2.6 GB | 3.7 GB | Fits | Get file → | |
| Q3_K_L | 2.6 GB | 3.7 GB | Fits | Get file → | |
| IQ4_NL | 2.7 GB | 3.8 GB | Fits | Get file → | |
| Q4_0 | 2.7 GB | 3.8 GB | Fits | Get file → | |
| Q4_K_S | 2.7 GB | 3.8 GB | Fits | Get file → | |
| Q4_K_M | 2.9 GB | 4.0 GB | Fits | Get file → | |
| Q3_K_XL | 2.9 GB | 4.0 GB | Fits | Get file → | |
| Q4_1 | 3.0 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_L | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_S | 3.2 GB | 4.3 GB | Fits | Get file → | |
| Q5_K_M | 3.3 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_L | 3.5 GB | 4.6 GB | Fits | Get file → | |
| Q6_K | 3.8 GB | 4.9 GB | Fits | Get file → | |
| Q6_K_L | 4.0 GB | 5.1 GB | Fits | Get file → | |
| Q8_0 | 4.9 GB | 6.0 GB | Fits | Get file → | |
| BF16 | 9.2 GB | 10.4 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_M (1.7 GB) or Q2_K (1.89 GB). For 16 GB VRAM, Q4_K_M (2.92 GB) or Q5_K_M (3.34 GB) are good choices. Higher precision quants like Q8_0 (4.92 GB) provide better quality but need more memory.
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 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
Source
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: file is 0.0 GB, 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 and 19 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 bartowski/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 IQ2_M or Q2_K quantizations which are 1.7 GB and 1.89 GB respectively.
Does AFM‑4.5B support vision tasks?
No, the model has no vision capabilities.
What sampling settings are recommended?
Temperature 0.5, top_k 50, top_p 0.95, repeat_penalty 1.1.