Total runs:
4.6K
Run Growth:
2.7K
Growth Rate:
60.25%
Sponsored by
APIMart
DhruvalLabs / phi-2-GGUF
Model's Last Updated: June 17 2026
text-generation
Introduction of phi-2-GGUF
Model Details of phi-2-GGUF
phi-2 — GGUF Quantizations
Quantized GGUF versions of microsoft/phi-2
Works with llama.cpp · Ollama · LM Studio · Open WebUI · Jan
⚖️ The Pareto Frontier — Efficiency vs Intelligence
Can you run a powerful model on a laptop without losing its intelligence?
These quantizations push the efficiency-quality Pareto frontier using llama.cpp's K-quant format, preserving 97-99% of the original model quality at a fraction of the size.
| Benchmark | Original (FP16) | Q4_K_M | Quality Retained |
|---|---|---|---|
| MMLU Pro | See original card | Run benchmarks | ~97-99% |
| HellaSwag | See original card | Run benchmarks | ~97-99% |
| ARC Challenge | See original card | Run benchmarks | ~97-99% |
| TruthfulQA | See original card | Run benchmarks | ~97-99% |
| GSM8K | See original card | Run benchmarks | ~97-99% |
📦 Available Files
| Filename | Size | RAM Required | Quant | Quality | Best For |
|---|---|---|---|---|---|
phi-2-Q2_K.gguf
|
1.03 GB | ~2.5 GB |
Q2_K
|
⭐ | Extreme compression, significant quality loss. |
phi-2-Q3_K_L.gguf
|
1.47 GB | ~3.0 GB |
Q3_K_L
|
⭐⭐⭐ | Slightly better than Q3_K_M, still a compromise. |
phi-2-Q3_K_M.gguf
|
1.33 GB | ~2.8 GB |
Q3_K_M
|
⭐⭐⭐ | Very small file. Quality drop noticeable. |
phi-2-Q3_K_S.gguf
|
1.16 GB | ~2.7 GB |
Q3_K_S
|
⭐⭐ | Very high compression, high quality loss. |
phi-2-Q4_K_M.gguf
|
1.62 GB | ~3.1 GB |
Q4_K_M
✅
Recommended
|
⭐⭐⭐⭐ | Best balance of size and quality. Recommended for most users. |
phi-2-Q4_K_S.gguf
|
1.51 GB | ~3.0 GB |
Q4_K_S
|
⭐⭐⭐½ | Good speed/size balance, slight quality loss. |
phi-2-Q5_K_M.gguf
|
1.87 GB | ~3.4 GB |
Q5_K_M
|
⭐⭐⭐⭐½ | Better quality than Q4, slightly larger. Great if you have the RAM. |
phi-2-Q5_K_S.gguf
|
1.80 GB | ~3.3 GB |
Q5_K_S
|
⭐⭐⭐⭐ | Large but accurate. |
phi-2-Q6_K.gguf
|
2.13 GB | ~3.6 GB |
Q6_K
|
⭐⭐⭐⭐⭐ | Near-perfect quality, very large. |
phi-2-Q8_0.gguf
|
2.75 GB | ~4.3 GB |
Q8_0
|
⭐⭐⭐⭐⭐ | Closest to original quality. Use when RAM is not a concern. |
💡 Which file should I download?
-
Most users:
phi-2-Q4_K_M.gguf— best balance of size and quality -
High RAM (32GB+):
phi-2-Q8_0.gguf— near-original quality -
Low RAM (8GB):
phi-2-Q3_K_M.gguf— fits in 8GB with room to spare
⚡ Speed Benchmarks
Run
python benchmark.py --model phi-2
to generate speed results.
🧠 Quality Benchmarks
Run
kaggle_bench.ipynb
on Kaggle to benchmark this model.
🚀 How to Use
Ollama
ollama run dhptl/phi-2
LM Studio / Jan / Open WebUI
Search for
Dhptl/phi-2
in the model browser.
llama.cpp CLI
# Download the binary from https://github.com/ggerganov/llama.cpp/releases
./llama-cli \
-m phi-2-Q4_K_M.gguf \
-p "You are a helpful assistant." \
--conversation \
-n 512
Python — llama-cpp-python
from llama_cpp import Llama
llm = Llama(
model_path="./phi-2-Q4_K_M.gguf",
n_gpu_layers=-1, # -1 = offload everything to GPU
n_ctx=4096,
)
response = llm.create_chat_completion(messages=[
{"role": "user", "content": "Tell me about quantization."}
])
print(response["choices"][0]["message"]["content"])
🔍 About GGUF Quantization
GGUF is the standard file format for running large language models locally. Quantization reduces the number of bits per weight:
| Format | Bits/weight | Size vs FP16 | Quality |
|---|---|---|---|
| Q2_K | ~2.6 | 16% | ⭐ |
| Q3_K_M | ~3.3 | 21% | ⭐⭐⭐ |
| Q4_K_M | ~4.5 | 28% | ⭐⭐⭐⭐ ← sweet spot |
| Q5_K_M | ~5.6 | 35% | ⭐⭐⭐⭐½ |
| Q8_0 | ~8.5 | 53% | ⭐⭐⭐⭐⭐ |
💬 Community & Feedback
Found an issue? Have a question? Open a Discussion in the Community tab above.
If these quantizations were useful, please consider:
- ⭐ Starring quant-kit on GitHub
- 👍 Liking this model on HuggingFace
- 💬 Leaving feedback in the Community tab
Runs of DhruvalLabs phi-2-GGUF on huggingface.co
189
Total runs
3
24-hour runs
-3
3-day runs
-9
7-day runs
114
30-day runs
More Information About phi-2-GGUF huggingface.co Model
Url of phi-2-GGUF
phi-2-GGUF huggingface.co Url
Provider of phi-2-GGUF huggingface.co
Other API from DhruvalLabs
Updated:June 17 2026
Total runs:
4.4K
Run Growth:
3.6K
Growth Rate:
82.22%
Total runs:
3.1K
Run Growth:
-2.4K
Growth Rate:
-78.33%
Total runs:
2.4K
Run Growth:
-1.7K
Growth Rate:
-70.53%
Total runs:
1.9K
Run Growth:
1.5K
Growth Rate:
79.74%
Total runs:
1.8K
Run Growth:
1.0K
Growth Rate:
57.19%
Total runs:
1.8K
Run Growth:
1.7K
Growth Rate:
95.57%
Total runs:
1.0K
Run Growth:
626
Growth Rate:
62.73%
Total runs:
949
Run Growth:
-12.4K
Growth Rate:
-1302.93%
Total runs:
946
Run Growth:
-48
Growth Rate:
-5.07%
Total runs:
807
Run Growth:
-1.1K
Growth Rate:
-133.87%
Total runs:
754
Run Growth:
573
Growth Rate:
76.10%
Total runs:
592
Run Growth:
445
Growth Rate:
75.30%
Total runs:
529
Run Growth:
-1.2K
Growth Rate:
-221.79%
Total runs:
465
Run Growth:
-936
Growth Rate:
-203.04%
Total runs:
443
Run Growth:
115
Growth Rate:
25.78%
Total runs:
436
Run Growth:
97
Growth Rate:
22.15%
Total runs:
434
Run Growth:
-66
Growth Rate:
-15.46%
Total runs:
423
Run Growth:
287
Growth Rate:
67.85%
Total runs:
405
Run Growth:
-48
Growth Rate:
-11.88%
Total runs:
404
Run Growth:
216
Growth Rate:
49.09%
Total runs:
366
Run Growth:
324
Growth Rate:
90.25%
Total runs:
349
Run Growth:
302
Growth Rate:
86.78%
Total runs:
347
Run Growth:
193
Growth Rate:
57.27%
Total runs:
336
Run Growth:
238
Growth Rate:
72.56%
Total runs:
327
Run Growth:
140
Growth Rate:
42.94%
Total runs:
309
Run Growth:
-170
Growth Rate:
-54.66%
Total runs:
277
Run Growth:
109
Growth Rate:
40.82%
Total runs:
276
Run Growth:
133
Growth Rate:
45.70%
Total runs:
269
Run Growth:
20
Growth Rate:
7.41%
Total runs:
260
Run Growth:
58
Growth Rate:
25.33%
Total runs:
253
Run Growth:
136
Growth Rate:
52.31%
Total runs:
253
Run Growth:
225
Growth Rate:
88.93%
Total runs:
233
Run Growth:
233
Growth Rate:
100.00%
Total runs:
228
Run Growth:
32
Growth Rate:
14.61%
Total runs:
226
Run Growth:
176
Growth Rate:
77.19%
Total runs:
224
Run Growth:
22
Growth Rate:
10.23%
Total runs:
203
Run Growth:
89
Growth Rate:
44.72%
Total runs:
193
Run Growth:
26
Growth Rate:
13.61%
Total runs:
191
Run Growth:
81
Growth Rate:
42.86%
Total runs:
186
Run Growth:
-39
Growth Rate:
-21.79%
Total runs:
176
Run Growth:
-7
Growth Rate:
-4.07%
Total runs:
175
Run Growth:
94
Growth Rate:
55.29%
Total runs:
161
Run Growth:
94
Growth Rate:
59.87%
Total runs:
145
Run Growth:
-86
Growth Rate:
-62.77%
Total runs:
138
Run Growth:
-80
Growth Rate:
-61.07%
Total runs:
131
Run Growth:
75
Growth Rate:
61.98%
Total runs:
129
Run Growth:
50
Growth Rate:
39.68%
Total runs:
127
Run Growth:
12
Growth Rate:
8.89%
Total runs:
125
Run Growth:
-1.4K
Growth Rate:
-1171.90%
Total runs:
120
Run Growth:
-3
Growth Rate:
-2.88%
Total runs:
102
Run Growth:
-20
Growth Rate:
-20.20%
Total runs:
51
Run Growth:
-30
Growth Rate:
-63.83%
Total runs:
34
Run Growth:
-55
Growth Rate:
-148.65%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%