megatron-GPT-2-345m-EvolInstruct needs about 1.6 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.2 GB (Q2_K) to 0.4 GB (Q8_0).
Megatron‑GPT‑2 345 M EvolInstruct – small, instruction‑tuned GPT‑2
Megatron‑GPT‑2‑345m‑EvolInstruct is a 0.406 B parameter GPT‑2 variant fine‑tuned on the Evol‑Instruct dataset. It supports 1024‑token context and is competitive with GPT‑2 large on Wikitext‑103. The model is available in multiple GGUF quantizations.
Good at
- Instruction following
- Text generation
- Lightweight deployment
Limits
- No vision support
- License unspecified
- Context limited to 1024 tokens
Best for
- Chatbots on low‑memory GPUs
- Rapid prototyping of instruction models
- Educational demos
Who it’s for. Developers needing a small, instruction‑tuned GPT‑2 model that fits in limited VRAM. Researchers testing fine‑tuning pipelines on a 0.406 B parameter base.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ3_XS | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ3_S | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_S | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ3_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q3_K | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ4_XS | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q3_K_L | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_0 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| IQ4_NL | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.9 GB | Fits | Get file → | |
| Q4_1 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q4_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_S | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_1 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.4 GB | 1.0 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.27 GB file, ~1.6 GB memory). For tighter budgets, Q2_K (0.18 GB file, ~1.5 GB memory) is suitable. Higher quality can be achieved with Q5_K_M (0.31 GB file, ~1.6 GB memory).
What GPU do you need for megatron-GPT-2-345m-EvolInstruct?
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 Q8_0 (0.4 GB file, about 1.7 GB in use).
Which megatron-GPT-2-345m-EvolInstruct quant should you choose?
Q4_K_M is the usual starting point for megatron-GPT-2-345m-EvolInstruct: it balances file size and quality well. Here it is a 0.3 GB file.
The Q8_0 file is 0.4 GB, about 1.6 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 Q2_K at 0.2 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
Frequently asked questions about megatron-GPT-2-345m-EvolInstruct
How much VRAM does megatron-GPT-2-345m-EvolInstruct need?
About 1.6 GB at Q4_K_M with an 8K context window. That is the 0.3 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 megatron-GPT-2-345m-EvolInstruct on an 8 GB GPU?
Yes, with Q8_0: the 0.4 GB file needs about 1.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of megatron-GPT-2-345m-EvolInstruct GGUF?
It depends on the quant: Q2_K is 0.2 GB, IQ3_XS is 0.2 GB, IQ3_S is 0.2 GB, Q3_K_S is 0.2 GB, IQ3_M is 0.2 GB, Q3_K is 0.2 GB and 16 more.
What context length does megatron-GPT-2-345m-EvolInstruct support?
The GGUF header lists a trained context length of 1,024 tokens (1K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.1 GB at 1K.
Where can I download megatron-GPT-2-345m-EvolInstruct GGUF?
The files are on Hugging Face in the RichardErkhov/KnutJaegersberg_-_megatron-GPT-2-345m-EvolInstruct-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Yes, the Q4_K_M quantization requires about 1.6 GB VRAM at 8k context, which fits in 8 GB.
Does this model support image inputs?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports a maximum of 1024 tokens.