selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

microsoft logo

Can the Arc A580 run UserLM-2.0?

UserLM-2.0·8B·Arc A580·8 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The Arc A580 runs UserLM-2.0 fully in VRAM at Q5_K_M (about 7.1 GB of 8.0 GB), at roughly 49 tokens/s.

best quant
Q5_K_M
needs
7.1 GB
usable
8.0 GB
est. speed
~49 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the UserLM-2.0 page →

Every quantisation of UserLM-2.0 on the Arc A580

QuantQualityMemoryFitSpeed
Q2_K Heavy loss4.1 GBfits~107 tok/s
Q3_K_M Noticeable loss5.3 GBfits~72 tok/s
Q4_K_M Small loss6.3 GBfits~58 tok/s
Q5_K_M pickNear-lossless7.1 GBfits~49 tok/s
Q6_K Near-lossless8.0 GBtight~43 tok/s
Q8_0 Lossless9.8 GBoffload~14 tok/s
FP16 / BF16 Lossless17 GBoffload~3.5 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 UserLM-2.0 on the Arc A580

Using Q5_K_M, the best fit for Arc A580.

llama.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf liodon-ai/UserLM-2.0-imatrix-GGUF:Q5_K_M

Needs a Vulkan build of llama.cpp. Downloads the GGUF on first run.

llama.cpp · Docker with Vulkandocs
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/UserLM-2.0-imatrix-GGUF:Q5_K_M --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/UserLM-2.0", 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 →
ModelParamsBest quantMemorySpeedLicence
8BQ5_K_M≈7.1 GBFits in memory~49 tok/sConditions
8.2BQ5_K_M≈7.3 GBFits in memory~48 tok/sCommercial OK
8BQ5_K_M≈7.1 GBFits in memory~49 tok/sConditions
7.6BQ6_K≈7.0 GBFits in memory~45 tok/sCommercial OK
9.4BQ4_K_M≈7.2 GBFits in memory~49 tok/sCommercial OK
7.2BQ6_K≈7.3 GBFits in memory~47 tok/sCommercial OK

Other GPUs that run UserLM-2.0

Frequently asked questions

Can the Arc A580 run UserLM-2.0?
Yes. The Arc A580 runs UserLM-2.0 fully in VRAM at Q5_K_M (about 7.1 GB of 8.0 GB), at roughly 49 tokens/s.
How fast does UserLM-2.0 run on the Arc A580?
An estimate from memory bandwidth gives about 49 tokens/s at Q5_K_M.
Which quantisation of UserLM-2.0 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.