Can the Instinct MI50 32GB run MLExpert?
MLExpert·34.7B (3.5B active)·Instinct MI50 32GB·32 GB VRAM
Yes. The Instinct MI50 32GB runs MLExpert fully in VRAM at Q5_K_M (about 28 GB of 32 GB), at roughly 229 tokens/s.
- best quant
- Q5_K_M
- needs
- 28 GB
- usable
- 32 GB
- est. speed
- ~229 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the MLExpert page →
Every quantisation of MLExpert on the Instinct MI50 32GB
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 15 GB | fits | ~496 tok/s |
| Q3_K_M | 18 GB | fits | ~334 tok/s |
| Q4_K_M | 23 GB | fits | ~269 tok/s |
| Q5_K_M pick | 28 GB | fits | ~229 tok/s |
| Q6_K | 31 GB | tight | ~198 tok/s |
| Q8_0 | 37 GB | offload | ~47 tok/s |
| FP16 / BF16 | 69 GB | too big | — |
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 MLExpert on the Instinct MI50 32GB
Using Q5_K_M, the best fit for Instinct MI50 32GB.
ollama run hf.co/bartowski/InternScience_MLExpert-GGUF:Q5_K_MOllama’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 bartowski/InternScience_MLExpert-GGUF:Q5_K_MNeeds 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 bartowski/InternScience_MLExpert-GGUF:Q5_K_M --host 0.0.0.0 --port 8080 -ngl 99Server and web UI on port 8080.
lms get bartowski/InternScience_MLExpert-GGUF@Q5_K_MThen load it from the LM Studio app or with `lms load`.
from transformers import pipeline
pipe = pipeline("text-generation", model="InternScience/MLExpert", 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 Instinct MI50 32GB comfortably
All that fit →| Model | Params | Best quant | Memory | Speed |
|---|---|---|---|---|
| 36BA3B | Q5_K_M | ≈26 GBFits in memory | ~264 tok/s | |
| 31.2BA4.6B | Q5_K_M | ≈29 GBFits in memory | ~172 tok/s | |
| 32.8B | Q6_K | ≈29 GBFits in memory | ~21 tok/s | |
| 39.8BA1.3B | Q5_K_M | ≈29 GBFits in memory | ~633 tok/s | |
| 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~126 tok/s | |
| 30.5BA3B | Q6_K | ≈26 GBFits in memory | ~228 tok/s |
Other GPUs that run MLExpert
Frequently asked questions
- Can the Instinct MI50 32GB run MLExpert?
- Yes. The Instinct MI50 32GB runs MLExpert fully in VRAM at Q5_K_M (about 28 GB of 32 GB), at roughly 229 tokens/s.
- How fast does MLExpert run on the Instinct MI50 32GB?
- An estimate from memory bandwidth gives about 229 tokens/s at Q5_K_M.
- Which quantisation of MLExpert should I use on the Instinct MI50 32GB?
- Q5_K_M: 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.