Can the Arc B580 run Groot-19B-A3B-261023?
Groot-19B-A3B-261023·19.4B (3B active)·Arc B580·12 GB VRAM
Yes, but only at Q3_K_M (about 11 GB of 12 GB), which costs noticeable quality, at roughly 171 tokens/s.
- best quant
- Q3_K_M
- needs
- 11 GB
- usable
- 12 GB
- est. speed
- ~171 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 Arc B580
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 8.8 GB | fits | ~254 tok/s |
| Q3_K_M pick | 11 GB | fits | ~171 tok/s |
| Q4_K_M | 13 GB | offload | ~83 tok/s |
| Q5_K_M | 16 GB | offload | ~47 tok/s |
| Q6_K | 18 GB | offload | ~33 tok/s |
| Q8_0 | 21 GB | offload | ~21 tok/s |
| FP16 / BF16 | 38 GB | too big | — |
Speed is a bandwidth-based estimate for generating text (456 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc B580
No community reports for this pair yet.
Report your own speed →Run Groot-19B-A3B-261023 on the Arc B580
Using Q3_K_M, the best fit for Arc B580.
ollama run hf.co/bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q3_K_MOllama’s ROCm/CUDA builds don’t cover this GPU. Recent Ollama releases use Vulkan when its Vulkan backend and driver are installed (older ones needed OLLAMA_VULKAN=1); llama.cpp or LM Studio with Vulkan are the safer bet.
llama-server -hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q3_K_MNeeds a Vulkan build of llama.cpp. Downloads the GGUF on first run.
docker run -d --name llama --device /dev/dri -p 8080:8080 \
-v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
ghcr.io/ggml-org/llama.cpp:server-vulkan \
-hf bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF:Q3_K_M --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get bartowski/GrootTeam_Groot-19B-A3B-261023-GGUF@Q3_K_MThen load it from the LM Studio app or with `lms load`.
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 Arc B580 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 12.2B | Q4_K_M | ≈10 GBFits in memory | ~34 tok/s | |
| 9.7B | Q8_0 | ≈11 GBFits in memory | ~24 tok/s | |
| 13.2B | Q4_K_M | ≈11 GBFits in memory | ~31 tok/s | |
| 8.8B | Q8_0 | ≈10 GBFits in memory | ~27 tok/s | |
| 10.7B | Q6_K | ≈10 GBFits in memory | ~29 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~25 tok/s |
Other GPUs that run Groot-19B-A3B-261023
Frequently asked questions
- Can the Arc B580 run Groot-19B-A3B-261023?
- Yes, but only at Q3_K_M (about 11 GB of 12 GB), which costs noticeable quality, at roughly 171 tokens/s.
- How fast does Groot-19B-A3B-261023 run on the Arc B580?
- An estimate from memory bandwidth gives about 171 tokens/s at Q3_K_M.
- Which quantisation of Groot-19B-A3B-261023 should I use on the Arc B580?
- Q3_K_M: the largest one that fits. Expected quality: noticeable loss 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.