Can the Arc A580 run plamo-3-8b-fin-instruct?
plamo-3-8b-fin-instruct·8.5B·Arc A580·8 GB VRAM
Yes. The Arc A580 runs plamo-3-8b-fin-instruct fully in VRAM at Q5_K_M (about 7.0 GB of 8.0 GB), at roughly 46 tokens/s.
- best quant
- Q5_K_M
- needs
- 7.0 GB
- usable
- 8.0 GB
- est. speed
- ~46 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the plamo-3-8b-fin-instruct page →
Every quantisation of plamo-3-8b-fin-instruct on the Arc A580
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 4.4 GB | fits | ~100 tok/s |
| Q3_K_M | 5.2 GB | fits | ~68 tok/s |
| Q4_K_M | 6.2 GB | fits | ~54 tok/s |
| Q5_K_M pick | 7.0 GB | fits | ~46 tok/s |
| Q6_K | 7.8 GB | tight | ~40 tok/s |
| Q8_0 | 9.9 GB | offload | ~13 tok/s |
| FP16 / BF16 | 18 GB | offload | ~3.2 tok/s |
Speed is a bandwidth-based estimate for generating text (512 GB/s); prompt processing and long contexts are slower.
Measured speed on the Arc A580
No community reports for this pair yet.
Report your own speed →Run plamo-3-8b-fin-instruct on the Arc A580
Using Q5_K_M, the best fit for Arc A580.
ollama run hf.co/mradermacher/plamo-3-8b-fin-instruct-GGUF:Q5_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 mradermacher/plamo-3-8b-fin-instruct-GGUF:Q5_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 mradermacher/plamo-3-8b-fin-instruct-GGUF:Q5_K_M --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get mradermacher/plamo-3-8b-fin-instruct-GGUF@Q5_K_MThen load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("text-generation", model="pfnet/plamo-3-8b-fin-instruct", 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 A580 comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 8.2B | Q5_K_M | ≈7.3 GBFits in memory | ~48 tok/s | |
| 8B | Q5_K_M | ≈7.1 GBFits in memory | ~49 tok/s | |
| 8B | Q5_K_M | ≈7.1 GBFits in memory | ~49 tok/s | |
| 7.6B | Q6_K | ≈7.0 GBFits in memory | ~45 tok/s | |
| 9.4B | Q4_K_M | ≈7.2 GBFits in memory | ~49 tok/s | |
| 8.8B | Q4_K_M | ≈7.0 GBFits in memory | ~53 tok/s |
Other GPUs that run plamo-3-8b-fin-instruct
Frequently asked questions
- Can the Arc A580 run plamo-3-8b-fin-instruct?
- Yes. The Arc A580 runs plamo-3-8b-fin-instruct fully in VRAM at Q5_K_M (about 7.0 GB of 8.0 GB), at roughly 46 tokens/s.
- How fast does plamo-3-8b-fin-instruct run on the Arc A580?
- An estimate from memory bandwidth gives about 46 tokens/s at Q5_K_M.
- Which quantisation of plamo-3-8b-fin-instruct should I use on the Arc A580?
- Q5_K_M: the largest one that fits. Expected quality: near-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.