Can the Radeon RX 6700 XT run lumi-4b?
lumi-4b·4B·Radeon RX 6700 XT·12 GB VRAM
Yes. The Radeon RX 6700 XT runs lumi-4b fully in VRAM at FP16 / BF16 (about 9.6 GB of 12 GB), at roughly 27 tokens/s.
- best quant
- FP16 / BF16
- needs
- 9.6 GB
- usable
- 12 GB
- est. speed
- ~27 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the lumi-4b page →
Every quantisation of lumi-4b on the Radeon RX 6700 XT
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.1 GB | fits | ~162 tok/s |
| Q3_K_M | 3.7 GB | fits | ~109 tok/s |
| Q4_K_M | 4.2 GB | fits | ~88 tok/s |
| Q5_K_M | 4.6 GB | fits | ~75 tok/s |
| Q6_K | 5.7 GB | fits | ~65 tok/s |
| Q8_0 | 5.9 GB | fits | ~50 tok/s |
| FP16 / BF16 pick | 9.6 GB | fits | ~27 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 lumi-4b on the Radeon RX 6700 XT
Using FP16 / BF16, the best fit for Radeon RX 6700 XT.
llama-server -hf Mateus-Nery/lumi-4b-GGUF:BF16Needs 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 Mateus-Nery/lumi-4b-GGUF:BF16 --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
vllm serve ceia-br/lumi-4bNeeds vLLM built for ROCm; it supports Instinct MI200/MI300 and Radeon RX 7900 / 9000 cards.
vllm serve liodon-ai/lumi-4b-FP8services:
vllm:
image: rocm/vllm:latest
command: vllm serve ceia-br/lumi-4b --host 0.0.0.0 --port 8000
ports:
- "8000:8000"
ipc: host
devices:
- /dev/kfd
- /dev/dri
group_add:
- video
security_opt:
- seccomp=unconfined
volumes:
- ~/.cache/huggingface:/root/.cache/huggingfaceAMD’s rocm/vllm image. API on port 8000.
sglang serve ceia-br/lumi-4b --host 0.0.0.0 --port 30000Needs SGLang’s ROCm build (Instinct MI300-class GPUs).
Chat models that fit the Radeon RX 6700 XT comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~49 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~62 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~52 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~49 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~48 tok/s | |
| 3.1B | Q8_0 | ≈4.3 GBFits in memory | ~64 tok/s |
Other GPUs that run lumi-4b
Frequently asked questions
- Can the Radeon RX 6700 XT run lumi-4b?
- Yes. The Radeon RX 6700 XT runs lumi-4b fully in VRAM at FP16 / BF16 (about 9.6 GB of 12 GB), at roughly 27 tokens/s.
- How fast does lumi-4b run on the Radeon RX 6700 XT?
- An estimate from memory bandwidth gives about 27 tokens/s at FP16 / BF16.
- Which quantisation of lumi-4b 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.