Phi 4 reasoning vision 15B needs ~13.0 GB VRAM. Radeon RX 7800M 12GB has 12.0 GB. With Q4_K_M quantization, expect ~18 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
1.0 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~0.7 GB host RAM)
Decode
17.6 tok/s
TTFT
10981 ms
Safe context
7K
Memory
13.0 GB / 12.0 GB
Offload
10%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 0.7 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs with offload (needs ~0.1 GB host RAM) | 20.4 tok/s | 5170 ms | 7K |
| Coding | D | Very compromised (needs ~0.7 GB host RAM) | 17.6 tok/s | 10981 ms | 7K |
| Agentic Coding | F | Too heavy | 13.5 tok/s | 20857 ms | 7K |
| Reasoning | D | Very compromised (needs ~0.7 GB host RAM) | 17.6 tok/s | 12978 ms | 7K |
| RAG | F | Too heavy | 13.5 tok/s | 26071 ms | 7K |
How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on Radeon RX 7800M 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C52 |
Q3_K_S | 3 | 7.4 GB | Low | C52 |
NVFP4Best for your GPU | 4 | 8.4 GB | Medium | C51 |
Q4_K_M | 4 | 9.2 GB | Medium | F0 |
Q5_K_M | 5 | 10.8 GB | High | F0 |
Q6_K | 6 | 12.3 GB | High | F0 |
Q8_0 | 8 | 16.1 GB | Very High | F0 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Copy-paste commands to run Phi 4 reasoning vision 15B on your machine.
Run
lms load hf-jamesburton--phi-4-reasoning-vision-15b-gguf && lms server startアップグレードオプション
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Adds memory headroom for longer context windows and future model growth.
〜$329 MSRP
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Adds memory headroom for longer context windows and future model growth.
〜$349 MSRP
Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 147%.
〜$479 MSRP
Yes, Radeon RX 7800M 12GB can run Phi 4 reasoning vision 15B with a D grade (Very compromised (needs ~0.7 GB host RAM)). Expected decode speed: 17.6 tok/s.
Phi 4 reasoning vision 15B (15B parameters) requires approximately 13.0 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 4 reasoning vision 15B is Q4_K_M, which balances quality and memory efficiency.
On Radeon RX 7800M 12GB, Phi 4 reasoning vision 15B achieves approximately 17.6 tokens per second decode speed with a time-to-first-token of 10981ms using Q4_K_M quantization.
For coding workloads, Phi 4 reasoning vision 15B on Radeon RX 7800M 12GB receives a D grade with 17.6 tok/s and 7K context.
On Radeon RX 7800M 12GB, Phi 4 reasoning vision 15B can safely use up to 7K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/hf-jamesburton--phi-4-reasoning-vision-15b-gguf-on-rx-7800m-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: