Can the Radeon RX 9070 XT run Spark-X2.6-4B-Base?
Spark-X2.6-4B-Base·4.1B·Radeon RX 9070 XT·16 GB VRAM
Yes. The Radeon RX 9070 XT runs Spark-X2.6-4B-Base fully in VRAM at FP16 / BF16 (about 9.7 GB of 16 GB), at roughly 43 tokens/s.
- best quant
- FP16 / BF16
- needs
- 9.7 GB
- usable
- 16 GB
- est. speed
- ~43 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the Spark-X2.6-4B-Base page →
Every quantisation of Spark-X2.6-4B-Base on the Radeon RX 9070 XT
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 3.4 GB | fits | ~260 tok/s |
| Q3_K_M | 3.8 GB | fits | ~175 tok/s |
| Q4_K_M | 4.2 GB | fits | ~141 tok/s |
| Q5_K_M | 4.5 GB | fits | ~120 tok/s |
| Q6_K | 4.9 GB | fits | ~104 tok/s |
| Q8_0 | 5.9 GB | fits | ~81 tok/s |
| FP16 / BF16 pick | 9.7 GB | fits | ~43 tok/s |
Speed is a bandwidth-based estimate for generating text (640 GB/s); prompt processing and long contexts are slower.
Measured speed on the Radeon RX 9070 XT
No community reports for this pair yet.
Report your own speed →Run Spark-X2.6-4B-Base on the Radeon RX 9070 XT
Using Q6_K, the best fit for Radeon RX 9070 XT.
ollama run hf.co/mradermacher/Spark-X2.6-4B-Base-i1-GGUF:Q6_Kdocker run -d --name ollama --device /dev/kfd --device /dev/dri \
-v ollama:/root/.ollama -p 11434:11434 ollama/ollama:rocm
docker exec -it ollama ollama run hf.co/mradermacher/Spark-X2.6-4B-Base-i1-GGUF:Q6_KThe image bundles the ROCm runtime; the host only needs the amdgpu kernel driver.
llama-server -hf mradermacher/Spark-X2.6-4B-Base-i1-GGUF:Q6_KNeeds a HIP (ROCm) build of llama.cpp. Downloads the GGUF on first run.
docker run -d --name llama --device /dev/kfd --device /dev/dri -p 8080:8080 \
-v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
ghcr.io/ggml-org/llama.cpp:server-rocm \
-hf mradermacher/Spark-X2.6-4B-Base-i1-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get mradermacher/Spark-X2.6-4B-Base-i1-GGUF@Q6_KThen load it from the LM Studio app or with `lms load`.
sglang serve XHToken/Spark-X2.6-4B-Base --host 0.0.0.0 --port 30000Needs SGLang’s ROCm build (Instinct MI300-class GPUs).
from transformers import pipeline
pipe = pipeline("text-generation", model="XHToken/Spark-X2.6-4B-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 9070 XT comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~82 tok/s | |
| 3.2B | Q8_0 | ≈4.7 GBFits in memory | ~103 tok/s | |
| 3.8B | Q8_0 | ≈5.5 GBFits in memory | ~86 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~81 tok/s | |
| 4B | Q8_0 | ≈5.8 GBFits in memory | ~82 tok/s | |
| 4.1B | Q8_0 | ≈5.9 GBFits in memory | ~81 tok/s |
Other GPUs that run Spark-X2.6-4B-Base
Frequently asked questions
- Can the Radeon RX 9070 XT run Spark-X2.6-4B-Base?
- Yes. The Radeon RX 9070 XT runs Spark-X2.6-4B-Base fully in VRAM at FP16 / BF16 (about 9.7 GB of 16 GB), at roughly 43 tokens/s.
- How fast does Spark-X2.6-4B-Base run on the Radeon RX 9070 XT?
- An estimate from memory bandwidth gives about 43 tokens/s at FP16 / BF16.
- Which quantisation of Spark-X2.6-4B-Base should I use on the Radeon RX 9070 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.