PH

dolphin-2.9.2-Phi-3-Medium-abliterated

PhiGGUF by legraphistaUpdated 2024-06-03
Download on Hugging Face
Parameters14B
Context4K
Layers40
Architecturellama
Smallest quant3.1 GB
Quick answer

dolphin-2.9.2-Phi-3-Medium-abliterated needs about 8.5 GB of memory at IQ3_M (a 6.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 3.1 GB (IQ1_S) to 27.9 GB.

14‑billion‑parameter Phi‑3‑Medium model with uncensored instruction and coding skills

Dolphin‑2.9.2‑Phi‑3‑Medium‑abliterated is a 14‑billion‑parameter Llama‑style model. It is fine‑tuned for instruction following, coding, and function calling. The model is released under the MIT license.

Good at

  • Instruction following
  • Coding tasks
  • Function calling

Limits

  • No vision support
  • Requires 8k context for full performance
  • Uncensored content may need alignment layer

Best for

  • Chatbot development
  • Code generation
  • API function integration

Who it’s for. Developers building chat or coding assistants who need a large, instruction‑oriented model. The model is suitable for users who can manage uncensored outputs responsibly.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S3.1 GB 4.4 GB
Fits Get file →
IQ1_M3.3 GB 4.7 GB
Fits Get file →
IQ2_XXS3.8 GB 5.1 GB
Fits Get file →
IQ2_XS4.2 GB 5.5 GB
Fits Get file →
IQ2_S4.4 GB 5.7 GB
Fits Get file →
IQ2_M4.8 GB 6.1 GB
Fits Get file →
Q2_K_S4.8 GB 6.2 GB
Fits Get file →
Q2_K5.2 GB 6.5 GB
Fits Get file →
IQ3_XXS5.4 GB 6.8 GB
Fits Get file →
IQ3_XS5.8 GB 7.1 GB
Fits Get file →
Q3_K_S6.1 GB 7.4 GB
Tight Get file →
IQ3_S6.1 GB 7.4 GB
Tight Get file →
IQ3_M6.3 GB 7.6 GB
Tight Get file →
Q3_K6.8 GB 8.1 GB
Too big Get file →
Q3_K_L7.3 GB 8.7 GB
Too big Get file →
IQ4_XS7.5 GB 8.8 GB
Too big Get file →
IQ4_NL7.9 GB 9.3 GB
Too big Get file →
Q4_K_S8.0 GB 9.3 GB
Too big Get file →
Q4_K8.4 GB 9.7 GB
Too big Get file →
Q5_K_S9.6 GB 11.0 GB
Too big Get file →
Q5_K9.9 GB 11.2 GB
Too big Get file →
Q6_K11.5 GB 12.8 GB
Too big Get file →
Q8_014.8 GB 16.2 GB
Too big Get file →
BF1627.9 GB 29.3 GB
Too big Get file →
—27.9 GB 29.3 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (3.05 GB, 5.2 GB memory) or IQ1_M (3.33 GB, 5.5 GB memory). For 16 GB VRAM IQ2_S (4.41 GB, 6.6 GB memory) or Q2_K (5.2 GB, 7.4 GB memory) are suitable. Higher quants like Q3_K (6.75 GB, 8.9 GB memory) fit 24 GB VRAM setups.

What GPU do you need for dolphin-2.9.2-Phi-3-Medium-abliterated?

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 IQ2_XXS (3.8 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ3_XS (5.8 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q5_K_S (9.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.5 GB file, about 13.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 17.0 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (27.9 GB file, about 30.1 GB in use).

Which dolphin-2.9.2-Phi-3-Medium-abliterated quant should you choose?

IQ3_M (6.3 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

If memory is tight, the smallest file is IQ1_S at 3.1 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

Architecturellama
Parameters14B
Layers40
Trained context4,096 tokens
KV cache (fp16)200 KB per token

Source

Quantized bylegraphista
FamilyPhi
Licensemit
Downloads (HF)1,205
Last updated2024-06-03

Frequently asked questions about dolphin-2.9.2-Phi-3-Medium-abliterated

How much VRAM does dolphin-2.9.2-Phi-3-Medium-abliterated need?

About 8.5 GB at IQ3_M with an 8K context window. That is the 6.3 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 dolphin-2.9.2-Phi-3-Medium-abliterated on an 8 GB GPU?

Yes, with IQ3_XS: the 5.8 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of dolphin-2.9.2-Phi-3-Medium-abliterated GGUF?

It depends on the quant: IQ1_S is 3.1 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.8 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.4 GB, IQ2_M is 4.8 GB and 19 more.

What context length does dolphin-2.9.2-Phi-3-Medium-abliterated support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.7 GB at 8K and 0.8 GB at 4K.

Where can I download dolphin-2.9.2-Phi-3-Medium-abliterated GGUF?

The files are on Hugging Face in the legraphista/dolphin-2.9.2-Phi-3-Medium-abliterated-IMat-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 dolphin-2.9.2-Phi-3-Medium-abliterated use?

Hugging Face lists the license as mit. 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 this model on 8 GB VRAM?

Yes, use IQ1_S or IQ1_M quantizations; they require about 5.2–5.5 GB memory at 8k context.

Does this model support vision?

No, the model has no vision capabilities.

What license does it use?

The model is released under the MIT license.

Other GGUFs of dolphin-2.9.2-Phi-3-Medium-abliterated

Similar models

Browse all →

More from legraphista

All by legraphista →

More Phi models

All Phi →

Other medium models

All medium models →