PH

JSL Med Phi 3.5 Mini v3

PhiGGUF by mradermacherUpdated 2024-09-17
Download on Hugging Face
Parameters3.82B
Context128K
Layers32
Architecturephi3
Smallest quant1.4 GB
Quick answer

JSL Med Phi 3.5 Mini v3 needs about 6.1 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 15 quants, from 1.4 GB (Q2_K) to 7.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.

JSL Med Phi 3.5 Mini v3 – a 3.82B Phi3 model in GGUF format

JSL Med Phi 3.5 Mini v3 is a 3.82B parameter Phi3 model trained on 131072 context tokens. It is available in multiple GGUF quantizations and is designed for medical language tasks. The model has no specified license and no vision capabilities.

Good at

  • Medical text generation
  • Clinical question answering
  • Contextual summarization

Limits

  • No vision support
  • Large context requires significant VRAM
  • License not specified

Best for

  • Medical note drafting
  • Clinical decision support
  • Patient FAQ generation

Who it’s for. Developers building medical LLM applications and researchers needing a Phi3 model for clinical text processing.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K1.4 GB 5.1 GB
Fits Get file →
IQ3_XS1.6 GB 5.3 GB
Fits Get file →
IQ3_S1.7 GB 5.4 GB
Fits Get file →
Q3_K_S1.7 GB 5.4 GB
Fits Get file →
IQ3_M1.9 GB 5.6 GB
Fits Get file →
Q3_K_M2.0 GB 5.7 GB
Fits Get file →
IQ4_XS2.1 GB 5.8 GB
Fits Get file →
Q3_K_L2.1 GB 5.8 GB
Fits Get file →
Q4_K_S2.2 GB 5.9 GB
Fits Get file →
Q4_K_M2.4 GB 6.1 GB
Fits Get file →
Q5_K_S2.6 GB 6.4 GB
Fits Get file →
Q5_K_M2.8 GB 6.5 GB
Fits Get file →
Q6_K3.1 GB 6.9 GB
Fits Get file →
Q8_04.1 GB 7.8 GB
Tight Get file →
F167.6 GB 11.4 GB
Too big Get file →

For 8 GB VRAM, Q4_K_M (file size 2.39 GB, estimated memory 6.1 GB at 8k context) is suitable. If memory is tighter, Q2_K (1.42 GB, 5.1 GB) or IQ3_XS (1.63 GB, 5.3 GB) are options. For higher quality, Q5_K_M (2.82 GB, 6.5 GB) can be used on 12 GB VRAM.

What GPU do you need for JSL Med Phi 3.5 Mini v3?

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 Q4_K_S (2.2 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is F16 (7.6 GB file, about 11.4 GB in use).

Which JSL Med Phi 3.5 Mini v3 quant should you choose?

Q4_K_M is the usual starting point for JSL Med Phi 3.5 Mini v3: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 4.1 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 Q2_K at 1.4 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

Architecturephi3
Parameters3.82B
Layers32
Trained context131,072 tokens
KV cache (fp16)384 KB per token

Source

Quantized bymradermacher
FamilyPhi
Downloads (HF)1,562
Last updated2024-09-17

Frequently asked questions about JSL Med Phi 3.5 Mini v3

How much VRAM does JSL Med Phi 3.5 Mini v3 need?

About 6.1 GB at Q4_K_M with an 8K context window. That is the 2.4 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 JSL Med Phi 3.5 Mini v3 on an 8 GB GPU?

Yes, with Q8_0: the 4.1 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of JSL Med Phi 3.5 Mini v3 GGUF?

It depends on the quant: Q2_K is 1.4 GB, IQ3_XS is 1.6 GB, IQ3_S is 1.7 GB, Q3_K_S is 1.7 GB, IQ3_M is 1.9 GB, Q3_K_M is 2.0 GB and 9 more.

What context length does JSL Med Phi 3.5 Mini v3 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.

Where can I download JSL Med Phi 3.5 Mini v3 GGUF?

The files are on Hugging Face in the mradermacher/JSL-Med-Phi-3.5-Mini-v3-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 Q4_K_M on 8 GB VRAM?

Estimated memory 6.1 GB at 8k context, so 8 GB VRAM is sufficient.

Is there a quant with less than 2 GB file size?

Yes, Q2_K is 1.42 GB and IQ3_XS is 1.63 GB.

Does the model support multi-part files?

Use TheBloke's READMEs for concatenation of multi-part files.

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Phi models

All Phi →

Other small models

All small models →