Can the Instinct MI50 32GB run ZwZ2-27B?
ZwZ2-27B·27.4B·Instinct MI50 32GB·32 GB VRAM
Yes. The Instinct MI50 32GB runs ZwZ2-27B fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 25 tokens/s.
- best quant
- Q6_K
- needs
- 24 GB
- usable
- 32 GB
- est. speed
- ~25 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the ZwZ2-27B page →
Every quantisation of ZwZ2-27B on the Instinct MI50 32GB
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 11 GB | fits | ~63 tok/s |
| Q3_K_M | 16 GB | fits | ~42 tok/s |
| Q4_K_M | 19 GB | fits | ~34 tok/s |
| Q5_K_M | 21 GB | fits | ~29 tok/s |
| Q6_K pick | 24 GB | fits | ~25 tok/s |
| Q8_0 | 30 GB | tight | ~19 tok/s |
| FP16 / BF16 | 55 GB | offload | ~1.3 tok/s |
Speed is a bandwidth-based estimate for generating text (1024 GB/s); prompt processing and long contexts are slower.
Measured speed on the Instinct MI50 32GB
No community reports for this pair yet.
Report your own speed →Run ZwZ2-27B on the Instinct MI50 32GB
Using Q6_K, the best fit for Instinct MI50 32GB.
llama-server -hf prithivMLmods/inclusionAI-ZwZ2-27B-GGUF:Q6_KNeeds 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 prithivMLmods/inclusionAI-ZwZ2-27B-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="inclusionAI/ZwZ2-27B", dtype="auto", device_map="auto")
messages = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
{"type": "text", "text": "Describe this image."},
],
}
]
out = pipe(text=messages, max_new_tokens=256)
print(out[0]["generated_text"][-1]["content"])Vision models that fit the Instinct MI50 32GB comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 27.8B | Q6_K | ≈25 GBFits in memory | ~25 tok/s | |
| 27.8B | Q6_K | ≈25 GBFits in memory | ~25 tok/s | |
| 25.8BA4B | Q8_0 | ≈29 GBFits in memory | ~133 tok/s | |
| 31.3B | Q5_K_M | ≈29 GBFits in memory | ~25 tok/s | |
| 27.4B | Q6_K | ≈26 GBFits in memory | ~25 tok/s | |
| 27.8B | Q6_K | ≈24 GBFits in memory | ~25 tok/s |
Other GPUs that run ZwZ2-27B
Frequently asked questions
- Can the Instinct MI50 32GB run ZwZ2-27B?
- Yes. The Instinct MI50 32GB runs ZwZ2-27B fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 25 tokens/s.
- How fast does ZwZ2-27B run on the Instinct MI50 32GB?
- An estimate from memory bandwidth gives about 25 tokens/s at Q6_K.
- Which quantisation of ZwZ2-27B should I use on the Instinct MI50 32GB?
- Q6_K: the largest one that fits. Expected quality: near-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.