Dolphin-2.9.1-Phi-3-Kensho-4.5B needs about 10.1 GB of memory at Q4_K_M (a 4.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 2.4 GB (Q2_K) to 6.9 GB (Q8_0).
Phi‑3 based 4.5B model with 6.54B parameters
Dolphin‑2.9.1‑Phi‑3‑Kensho‑4.5B is a 6.54B‑parameter LLM built on the Phi architecture. It supports a 4096‑token context window and is available in multiple GGUF quantizations.
Good at
- Large context handling
- Efficient inference on modest GPUs
- Versatile language support
Limits
- No vision capabilities
- License not specified
- Requires 8‑k context for memory estimates
Best for
- Chatbot development
- Text summarization
- Code generation
Who it’s for. Developers needing a balance between performance and memory usage. Suitable for projects that can run on consumer GPUs with 8‑k context support.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.4 GB | 5.8 GB | Fits | Get file → | |
| Q3_K_S | 2.9 GB | 6.2 GB | Fits | Get file → | |
| Q3_K_M | 3.2 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_L | 3.5 GB | 6.8 GB | Fits | Get file → | |
| Q4_0 | 3.7 GB | 7.0 GB | Fits | Get file → | |
| Q4_K_S | 3.7 GB | 7.1 GB | Fits | Get file → | |
| Q4_K_M | 4.0 GB | 7.3 GB | Tight | Get file → | |
| Q4_1 | 4.1 GB | 7.4 GB | Tight | Get file → | |
| Q5_0 | 4.5 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_S | 4.5 GB | 7.8 GB | Tight | Get file → | |
| Q5_K_M | 4.6 GB | 8.0 GB | Tight | Get file → | |
| Q5_1 | 4.9 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 5.4 GB | 8.7 GB | Too big | Get file → | |
| Q8_0 | 6.9 GB | 10.3 GB | Too big | Get file → |
For 8‑GB VRAM, Q2_K (2.45 GB) or Q3_K_S (2.85 GB) are suitable. If 12‑GB VRAM is available, Q4_K_M (3.96 GB) or Q5_K_M (4.64 GB) provide better quality. Larger quants exceed typical consumer GPU limits.
What GPU do you need for Dolphin-2.9.1-Phi-3-Kensho-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: 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: the best quant that fits is Q6_K (5.4 GB file, about 11.5 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (6.9 GB file, about 13.1 GB in use).
Which Dolphin-2.9.1-Phi-3-Kensho-4.5B quant should you choose?
Q4_K_M is the usual starting point for Dolphin-2.9.1-Phi-3-Kensho-4.5B: it balances file size and quality well. Here it is a 4.0 GB file.
The Q8_0 file is 6.9 GB, about 1.8 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 2.4 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 Dolphin-2.9.1-Phi-3-Kensho-4.5B
How much VRAM does Dolphin-2.9.1-Phi-3-Kensho-4.5B need?
About 10.1 GB at Q4_K_M with an 8K context window. That is the 4.0 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 Dolphin-2.9.1-Phi-3-Kensho-4.5B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Dolphin-2.9.1-Phi-3-Kensho-4.5B GGUF?
It depends on the quant: Q2_K is 2.4 GB, Q3_K_S is 2.9 GB, Q3_K_M is 3.2 GB, Q3_K_L is 3.5 GB, Q4_0 is 3.7 GB, Q4_K_S is 3.7 GB and 8 more.
What context length does Dolphin-2.9.1-Phi-3-Kensho-4.5B support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 5.6 GB at 8K and 2.8 GB at 4K.
Where can I download Dolphin-2.9.1-Phi-3-Kensho-4.5B GGUF?
The files are on Hugging Face in the crusoeai/Dolphin-2.9.1-Phi-3-Kensho-4.5B-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 Q2_K quant file is 2.45 GB and requires about 8.6 GB memory at 8‑k context, which fits within 8 GB VRAM with some overhead.
What context length does this model support?
It supports up to 4096 tokens, as specified in its training context.
Does this model have vision capabilities?
No, the model does not support vision inputs.