Instructions to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
llama cli -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./llama-cli -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

Use Docker

docker model run hf.co/kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

LM Studio
Jan

vLLM

How to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

Ollama
How to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with Ollama:
```
ollama run hf.co/kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP
```

Unsloth Studio

How to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF to start chatting

Docker Model Runner
How to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP
```

Lemonade

How to use kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF:Q4_0_ROCMFP

Run and chat with the model

lemonade run user.Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF-Q4_0_ROCMFP

List all available models

lemonade list

Atomic Chat

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

⚠️ -fa off is required — flash attention breaks the vision path on gfx1151.

🚀 24.62 tok/s — +9.4% faster and 0.5 GiB smaller than Q4_K_M, ranges disjoint.

Phi-4-Reasoning-Vision-15B — ROCmFP4 (tier 102 `COHERENT`) GGUF

A 4-bit ROCmFP4 quantization for AMD gfx1151 (Ryzen AI MAX+ 395 / Strix Halo), quantized from F16 GGUF (27.96 GiB) — a lossless source, not a requantization of a lower-bit build.


File	`Phi-4-reasoning-vision-15B-Q4_0_ROCMFP4_COHERENT.gguf`
Size	8.0 GiB
BPW	4.65
ftype	`Q4_0_ROCMFP4_COHERENT` (102)

⛔ Requires a llama.cpp with the ROCmFP4 quant types

Q4_0_ROCMFP4_COHERENT (ftype 102) exists only in charlie12345/ROCmFPX, not upstream llama.cpp. Ignore the auto-generated "Use this model" commands above.

All quant variants

Three builds, all measured in one session on one box with one binary (Ryzen AI MAX+ 395, gfx1151, ROCm 7.2.4, ROCmFPX-2809dc5, -fa off) — so these rows are directly comparable. Median of 3, warm-up discarded, otherwise-idle box.

variant	ftype	size	bpw	decode (median)	range	repo
4-bit COHERENT	102	7.93 GiB	4.65	24.91	24.88 – 24.91	link
8-bit AGENT	115	14.34 GiB	8.40	14.08	14.06 – 14.09	link
8-bit plain	111	14.11 GiB	8.27	14.15	14.13 – 14.20	link

⚠️ The 4-bit build is ~1.7× faster and 43% smaller. The 8-bit builds exist for accuracy headroom, not throughput. The two 8-bit builds are within noise of each other (14.08 vs 14.15, ranges touching) — this model has no MTP draft head, and AGENT's benefit shows up in draft acceptance, so there is nothing here for it to win.

⚠️ -fa off is mandatory — flash attention breaks the vision path on gfx1151. The BF16 mmproj (862 MiB) ships in every one of these repos and is required for vision.

Measured

Ryzen AI MAX+ 395 (gfx1151, 128 GB unified, ROCm 7.2.4). Median of 3+, warm-up discarded, otherwise-idle box. Correctness at the model's official sampling.

build	size	decode (median)	range
this build	8.0 GiB	24.62	[23.42 – 25.37]
Q4_K_M	8.5 GiB	22.50	[22.25 – 22.50]

+9.4%, ranges disjoint. Vision verified: an 8×8 red PNG is correctly described as Red.

Correctness: 17×23 ⇒ ✅ 391 · capital of Japan ⇒ ✅ Tokyo · days in 2024 ⇒ ✅ 366

Per-tensor types (audited in the finished file)

output.weight Q6_K · token_embd Q6_K · norms F32 · bulk TYPE_100 (160) · vision tower kept at BF16 (mmproj, 823 MiB — included)

Serve with -fa off and the bundled BF16 mmproj.

What was NOT measured

No perplexity run, and no quality A/B against the baseline or the source. The checks above are memorized-fact prompts — necessary but not sufficient; a damaged model can pass them.
No long-context testing.
No tool-calling evaluation.

Base model licence inherited; credit for the model goes to its authors.

Downloads last month: 129

GGUF

Model size

15B params

Architecture

phi3

Hardware compatibility

4-bit

8-bit

Model tree for kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF

Base model

microsoft/phi-4

Finetuned

microsoft/Phi-4-reasoning

Finetuned

microsoft/Phi-4-reasoning-vision-15B

Quantized

(8)

this model

kingjones777
/

Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF

⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL

Phi-4-Reasoning-Vision-15B — ROCmFP4 (tier 102 `COHERENT`) GGUF

⛔ Requires a llama.cpp with the ROCmFP4 quant types

All quant variants

Measured

Per-tensor types (audited in the finished file)

What was NOT measured

Model tree for kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF

⚠️ STOCK llama.cpp WILL NOT LOAD THIS MODEL

Phi-4-Reasoning-Vision-15B — ROCmFP4 (tier 102 COHERENT) GGUF

⛔ Requires a llama.cpp with the ROCmFP4 quant types

All quant variants

Measured

Per-tensor types (audited in the finished file)

What was NOT measured

Model tree for kingjones777/Phi-4-Reasoning-Vision-15B-ROCmFP4-GGUF

⚠️ STOCK `llama.cpp` WILL NOT LOAD THIS MODEL

Phi-4-Reasoning-Vision-15B — ROCmFP4 (tier 102 `COHERENT`) GGUF