Can the Radeon RX 6700 XT run LFM3-1.7B-Base?
LFM3-1.7B-Base·1.7B·Radeon RX 6700 XT·12 GB VRAM
Yes. The Radeon RX 6700 XT runs LFM3-1.7B-Base fully in VRAM at FP16 / BF16 (about 4.3 GB of 12 GB), at roughly 61 tokens/s.
- best quant
- FP16 / BF16
- needs
- 4.3 GB
- usable
- 12 GB
- est. speed
- ~61 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 Radeon RX 6700 XT
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 1.6 GB | fits | ~372 tok/s |
| Q3_K_M | 1.8 GB | fits | ~250 tok/s |
| Q4_K_M | 1.9 GB | fits | ~202 tok/s |
| Q5_K_M | 2.1 GB | fits | ~172 tok/s |
| Q6_K | 2.3 GB | fits | ~148 tok/s |
| Q8_0 | 2.7 GB | fits | ~115 tok/s |
| FP16 / BF16 pick | 4.3 GB | fits | ~61 tok/s |
Speed is a bandwidth-based estimate for generating text (384 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 6700 XT
No community reports for this pair yet.
Report your own speed →Run LFM3-1.7B-Base on the Radeon RX 6700 XT
Using FP16 / BF16, the best fit for Radeon RX 6700 XT.
ollama run lfm3:1.7bThe library build picks its own default quantisation.
ollama run hf.co/mradermacher/LFM3-1.7B-Base-GGUF:F16docker run -d --name ollama --device /dev/kfd --device /dev/dri \
-e HSA_OVERRIDE_GFX_VERSION=10.3.0 \
-v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run lfm3:1.7bROCm doesn’t ship kernels for this card; -e HSA_OVERRIDE_GFX_VERSION=10.3.0 makes it run as the nearest supported target.
llama-server -hf mradermacher/LFM3-1.7B-Base-GGUF:F16Needs a HIP (ROCm) build of llama.cpp. Start it with HSA_OVERRIDE_GFX_VERSION=10.3.0 in front for this card. Downloads the GGUF on first run.
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
-e HSA_OVERRIDE_GFX_VERSION=10.3.0 \
-v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
ghcr.io/ggml-org/llama.cpp:server-rocm \
-hf mradermacher/LFM3-1.7B-Base-GGUF:F16 --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 Radeon RX 6700 XT comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 1.7B | Q8_0 | ≈2.7 GBFits in memory | ~115 tok/s | |
| 2B | Q8_0 | ≈3.2 GBFits in memory | ~98 tok/s | |
| 1.5B | Q8_0 | ≈2.6 GBFits in memory | ~129 tok/s | |
| 1.2B | Q8_0 | ≈2.0 GBFits in memory | ~161 tok/s | |
| 1B | Q8_0 | ≈1.8 GBFits in memory | ~199 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~62 tok/s |
Other GPUs that run LFM3-1.7B-Base
Frequently asked questions
- Can the Radeon RX 6700 XT run LFM3-1.7B-Base?
- Yes. The Radeon RX 6700 XT runs LFM3-1.7B-Base fully in VRAM at FP16 / BF16 (about 4.3 GB of 12 GB), at roughly 61 tokens/s.
- How fast does LFM3-1.7B-Base run on the Radeon RX 6700 XT?
- An estimate from memory bandwidth gives about 61 tokens/s at FP16 / BF16.
- Which quantisation of LFM3-1.7B-Base should I use on the Radeon RX 6700 XT?
- 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.