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.

LiquidAI logo

Can the Arc A310 run LFM3-1.7B?

LFM3-1.7B·1.7B·Arc A310·4 GB VRAM

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

Yes. The Arc A310 runs LFM3-1.7B fully in VRAM at Q8_0 (about 2.7 GB of 4.0 GB), at roughly 37 tokens/s.

best quant
Q8_0
needs
2.7 GB
usable
4.0 GB
est. speed
~37 tok/s

Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the LFM3-1.7B page →

Every quantisation of LFM3-1.7B on the Arc A310

QuantQualityMemoryFitSpeed
Q2_K Heavy loss1.6 GBfits~120 tok/s
Q3_K_M Noticeable loss1.7 GBfits~81 tok/s
Q4_K_M Small loss1.9 GBfits~65 tok/s
Q5_K_M Near-lossless2.1 GBfits~55 tok/s
Q6_K Near-lossless2.3 GBfits~48 tok/s
Q8_0 pickLossless2.7 GBfits~37 tok/s
FP16 / BF16 Lossless4.3 GBoffload~18 tok/s

Speed is a bandwidth-based estimate for generating text (124 GB/s); prompt processing and long contexts are slower.

Measured speed on the Arc A310

No community reports for this pair yet.

Report your own speed →

Run LFM3-1.7B on the Arc A310

Using Q8_0, the best fit for Arc A310.

Ollama · From the Ollama librarydocs
ollama run lfm3:1.7b

The library build picks its own default quantisation. Ollama’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.

Ollama · Q8_0 straight from Hugging Facedocs
ollama run hf.co/LiquidAI/LFM3-1.7B-GGUF:Q8_0

Ollama’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.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf LiquidAI/LFM3-1.7B-GGUF:Q8_0

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 LiquidAI/LFM3-1.7B-GGUF:Q8_0 --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

LM Studio · Download with the lms CLIdocs
lms get LiquidAI/LFM3-1.7B-GGUF@Q8_0

Then load it from the LM Studio app or with `lms load`.

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="LiquidAI/LFM3-1.7B", 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 A310 comfortably

All that fit →
ModelParamsBest quantMemorySpeedLicence
1.5BQ8_0≈2.6 GBFits in memory~42 tok/sCommercial OK
2BQ8_0≈3.2 GBFits in memory~32 tok/sCommercial OK
HuggingFaceTB logoSmolLM2-1.7BHuggingFaceTB
1.7BQ8_0≈3.8 GBFits in memory~38 tok/sCommercial OK
1.2BQ8_0≈2.0 GBFits in memory~52 tok/sConditions
1.7BQ8_0≈2.7 GBFits in memory~37 tok/sConditions
2.5BQ8_0≈3.5 GBFits in memory~26 tok/sCommercial OK

Other GPUs that run LFM3-1.7B

Frequently asked questions

Can the Arc A310 run LFM3-1.7B?
Yes. The Arc A310 runs LFM3-1.7B fully in VRAM at Q8_0 (about 2.7 GB of 4.0 GB), at roughly 37 tokens/s.
How fast does LFM3-1.7B run on the Arc A310?
An estimate from memory bandwidth gives about 37 tokens/s at Q8_0.
Which quantisation of LFM3-1.7B should I use on the Arc A310?
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.