Can the Arc A310 run LFM3-1.7B-Base?
LFM3-1.7B-Base·1.7B·Arc A310·4 GB VRAM
Yes. The Arc A310 runs LFM3-1.7B-Base 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-Base page →
Every quantisation of LFM3-1.7B-Base on the Arc A310
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.6 GB | fits | ~120 tok/s |
| Q3_K_M | 1.8 GB | fits | ~81 tok/s |
| Q4_K_M | 1.9 GB | fits | ~65 tok/s |
| Q5_K_M | 2.1 GB | fits | ~55 tok/s |
| Q6_K | 2.3 GB | fits | ~48 tok/s |
| Q8_0 pick | 2.7 GB | fits | ~37 tok/s |
| FP16 / BF16 | 4.3 GB | offload | ~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-Base on the Arc A310
Using Q8_0, the best fit for Arc A310.
ollama run lfm3:1.7bThe 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 run hf.co/mradermacher/LFM3-1.7B-Base-GGUF:Q8_0Ollama’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/LFM3-1.7B-Base-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 mradermacher/LFM3-1.7B-Base-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="LiquidAI/LFM3-1.7B-Base", 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 →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 1.7B | Q8_0 | ≈2.7 GBFits in memory | ~37 tok/s | |
| 1.5B | Q8_0 | ≈2.6 GBFits in memory | ~42 tok/s | |
| 2B | Q8_0 | ≈3.2 GBFits in memory | ~32 tok/s | |
| 1.7B | Q8_0 | ≈3.8 GBFits in memory | ~38 tok/s | |
| 1.2B | Q8_0 | ≈2.0 GBFits in memory | ~52 tok/s | |
| 2.5B | Q8_0 | ≈3.5 GBFits in memory | ~26 tok/s |
Other GPUs that run LFM3-1.7B-Base
Frequently asked questions
- Can the Arc A310 run LFM3-1.7B-Base?
- Yes. The Arc A310 runs LFM3-1.7B-Base 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-Base run on the Arc A310?
- An estimate from memory bandwidth gives about 37 tokens/s at Q8_0.
- Which quantisation of LFM3-1.7B-Base 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.