Can the Arc B580 run granite-4.1-3b-llmon-preview?
granite-4.1-3b-llmon-preview·3.7B·Arc B580·12 GB VRAM
Yes. The Arc B580 runs granite-4.1-3b-llmon-preview fully in VRAM at FP16 / BF16 (about 8.3 GB of 12 GB), at roughly 34 tokens/s.
- best quant
- FP16 / BF16
- needs
- 8.3 GB
- usable
- 12 GB
- est. speed
- ~34 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the granite-4.1-3b-llmon-preview page →
Every quantisation of granite-4.1-3b-llmon-preview on the Arc B580
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 2.6 GB | fits | ~208 tok/s |
| Q3_K_M | 2.9 GB | fits | ~140 tok/s |
| Q4_K_M | 3.3 GB | fits | ~113 tok/s |
| Q5_K_M | 3.7 GB | fits | ~96 tok/s |
| Q6_K | 4.1 GB | fits | ~83 tok/s |
| Q8_0 | 4.9 GB | fits | ~64 tok/s |
| FP16 / BF16 pick | 8.3 GB | fits | ~34 tok/s |
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 granite-4.1-3b-llmon-preview on the Arc B580
Using Q8_0, the best fit for Arc B580.
llama-server -hf liodon-ai/granite-4.1-3b-llmon-preview-GGUF:Q8_0Needs 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 liodon-ai/granite-4.1-3b-llmon-preview-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
from transformers import pipeline
pipe = pipeline("text-generation", model="ibm-granite/granite-4.1-3b-llmon-preview", dtype="auto", device_map="auto")
messages = [{"role": "user", "content": "Explain self-hosting in one paragraph."}]
out = pipe(messages, max_new_tokens=512)
print(out[0]["generated_text"][-1]["content"])Chat models that fit the Arc B580 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~59 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~73 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~62 tok/s | |
| 3.1B | Q8_0 | ≈4.3 GBFits in memory | ~76 tok/s | |
| 3.7B | Q8_0 | ≈4.9 GBFits in memory | ~64 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~59 tok/s |
Other GPUs that run granite-4.1-3b-llmon-preview
Frequently asked questions
- Can the Arc B580 run granite-4.1-3b-llmon-preview?
- Yes. The Arc B580 runs granite-4.1-3b-llmon-preview fully in VRAM at FP16 / BF16 (about 8.3 GB of 12 GB), at roughly 34 tokens/s.
- How fast does granite-4.1-3b-llmon-preview run on the Arc B580?
- An estimate from memory bandwidth gives about 34 tokens/s at FP16 / BF16.
- Which quantisation of granite-4.1-3b-llmon-preview should I use on the Arc B580?
- FP16 / BF16: 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.