Can the Radeon RX 7800 XT run KORMo-Web-11B?
KORMo-Web-11B·11.2B·Radeon RX 7800 XT·16 GB VRAM
Yes. The Radeon RX 7800 XT runs KORMo-Web-11B fully in VRAM at Q8_0 (about 13 GB of 16 GB), at roughly 29 tokens/s.
- best quant
- Q8_0
- needs
- 13 GB
- usable
- 16 GB
- est. speed
- ~29 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the KORMo-Web-11B page →
Every quantisation of KORMo-Web-11B on the Radeon RX 7800 XT
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 5.3 GB | fits | ~93 tok/s |
| Q3_K_M | 7.1 GB | fits | ~63 tok/s |
| Q4_K_M | 8.4 GB | fits | ~51 tok/s |
| Q5_K_M | 9.5 GB | fits | ~43 tok/s |
| Q6_K | 11 GB | fits | ~37 tok/s |
| Q8_0 pick | 13 GB | fits | ~29 tok/s |
| FP16 / BF16 | 24 GB | offload | ~3.8 tok/s |
Speed is a bandwidth-based estimate for generating text (624 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 7800 XT
No community reports for this pair yet.
Report your own speed →Run KORMo-Web-11B on the Radeon RX 7800 XT
vllm serve KORMo-VL/KORMo-Web-11BNeeds vLLM built for ROCm; it supports Instinct MI200/MI300 and Radeon RX 7900 / 9000 cards.
services:
vllm:
image: rocm/vllm:latest
command: vllm serve KORMo-VL/KORMo-Web-11B --host 0.0.0.0 --port 8000
ports:
- "8000:8000"
ipc: host
devices:
- /dev/kfd
- /dev/dri
group_add:
- video
security_opt:
- seccomp=unconfined
volumes:
- ~/.cache/huggingface:/root/.cache/huggingfaceAMD’s rocm/vllm image. API on port 8000.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="KORMo-VL/KORMo-Web-11B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the Radeon RX 7800 XT comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~33 tok/s | |
| 12.2B | Q6_K | ≈13 GBFits in memory | ~34 tok/s | |
| 8.8B | Q8_0 | ≈10 GBFits in memory | ~37 tok/s | |
| 10.7B | Q8_0 | ≈12 GBFits in memory | ~30 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~34 tok/s | |
| 8.3B | Q8_0 | ≈8.9 GBFits in memory | ~39 tok/s |
Other GPUs that run KORMo-Web-11B
Frequently asked questions
- Can the Radeon RX 7800 XT run KORMo-Web-11B?
- Yes. The Radeon RX 7800 XT runs KORMo-Web-11B fully in VRAM at Q8_0 (about 13 GB of 16 GB), at roughly 29 tokens/s.
- How fast does KORMo-Web-11B run on the Radeon RX 7800 XT?
- An estimate from memory bandwidth gives about 29 tokens/s at Q8_0.
- Which quantisation of KORMo-Web-11B should I use on the Radeon RX 7800 XT?
- Q8_0: the largest one that fits. Expected quality: lossless compared with the full-precision weights.
Memory and speed are estimates from the model's size and the card's memory bandwidth; real numbers depend on the runtime, drivers and context length. Community figures are medians of user reports.