Can the Radeon RX 7900 XTX run Groot-19B-A3B-261023?
Groot-19B-A3B-261023·19.4B (3B active)·Radeon RX 7900 XTX·24 GB VRAM
Yes. The Radeon RX 7900 XTX runs Groot-19B-A3B-261023 fully in VRAM at Q8_0 (about 21 GB of 24 GB), at roughly 166 tokens/s.
- best quant
- Q8_0
- needs
- 21 GB
- usable
- 24 GB
- est. speed
- ~166 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Groot-19B-A3B-261023 page →
Every quantisation of Groot-19B-A3B-261023 on the Radeon RX 7900 XTX
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 8.8 GB | fits | ~535 tok/s |
| Q3_K_M | 11 GB | fits | ~360 tok/s |
| Q4_K_M | 13 GB | fits | ~290 tok/s |
| Q5_K_M | 16 GB | fits | ~247 tok/s |
| Q6_K | 18 GB | fits | ~214 tok/s |
| Q8_0 pick | 21 GB | fits | ~166 tok/s |
| FP16 / BF16 | 38 GB | offload | ~13 tok/s |
Speed is a bandwidth-based estimate for generating text (960 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 7900 XTX
No community reports for this pair yet.
Report your own speed →Run Groot-19B-A3B-261023 on the Radeon RX 7900 XTX
Using Q8_0, the best fit for Radeon RX 7900 XTX.
ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0docker run -d --name ollama --device /dev/kfd --device /dev/dri \
-v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0The image bundles the ROCm runtime; the host only needs the amdgpu kernel driver.
llama-server -hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0Needs a HIP (ROCm) build of llama.cpp. Downloads the GGUF on first run.
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
-v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
ghcr.io/ggml-org/llama.cpp:server-rocm \
-hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF@Q8_0Then load it from the LM Studio app or with `lms load`.
vllm serve GrootTeam/Groot-19B-A3B-261023Needs vLLM built for ROCm; it supports Instinct MI200/MI300 and Radeon RX 7900 / 9000 cards.
services:
vllm:
image: rocm/vllm:latest
command: vllm serve GrootTeam/Groot-19B-A3B-261023 --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.
sglang serve GrootTeam/Groot-19B-A3B-261023 --host 0.0.0.0 --port 30000Needs SGLang’s ROCm build (Instinct MI300-class GPUs).
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="GrootTeam/Groot-19B-A3B-261023", 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 7900 XTX comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 25.8BA4B | Q5_K_M | ≈20 GBFits in memory | ~186 tok/s | |
| 27.8B | Q5_K_M | ≈22 GBFits in memory | ~27 tok/s | |
| 27.8B | Q5_K_M | ≈22 GBFits in memory | ~27 tok/s | |
| 27.4B | Q4_K_M | ≈21 GBFits in memory | ~32 tok/s | |
| 27.8B | Q5_K_M | ≈22 GBFits in memory | ~27 tok/s | |
| 29.8B | Q5_K_M | ≈22 GBFits in memory | ~25 tok/s |
Other GPUs that run Groot-19B-A3B-261023
Frequently asked questions
- Can the Radeon RX 7900 XTX run Groot-19B-A3B-261023?
- Yes. The Radeon RX 7900 XTX runs Groot-19B-A3B-261023 fully in VRAM at Q8_0 (about 21 GB of 24 GB), at roughly 166 tokens/s.
- How fast does Groot-19B-A3B-261023 run on the Radeon RX 7900 XTX?
- An estimate from memory bandwidth gives about 166 tokens/s at Q8_0.
- Which quantisation of Groot-19B-A3B-261023 should I use on the Radeon RX 7900 XTX?
- 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.