selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

HemmingwayAI logo

Can the Instinct MI50 32GB run Hemmingway-1.5?

Hemmingway-1.5·26.9B·Instinct MI50 32GB·32 GB VRAM

Saved in this browser, used on every model page.
Yes

Yes. The Instinct MI50 32GB runs Hemmingway-1.5 fully in VRAM at Q6_K (about 26 GB of 32 GB), at roughly 25 tokens/s.

best quant
Q6_K
needs
26 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 Hemmingway-1.5 page →

Every quantisation of Hemmingway-1.5 on the Instinct MI50 32GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss13 GBfits~64 tok/s
Q3_K_M Noticeable loss16 GBfits~43 tok/s
Q4_K_M Small loss20 GBfits~35 tok/s
Q5_K_M Near-lossless23 GBfits~29 tok/s
Q6_K pickNear-lossless26 GBfits~25 tok/s
Q8_0 Lossless31 GBtight~20 tok/s
FP16 / BF16 Lossless56 GBoffload~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 Hemmingway-1.5 on the Instinct MI50 32GB

Using Q6_K, the best fit for Instinct MI50 32GB.

Ollama · Q6_K straight from Hugging Facedocs
ollama run hf.co/bartowski/HemmingwayAI_Hemmingway-1.5-GGUF:Q6_K

Ollama’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.cpp · OpenAI-compatible server with a web UIdocs
llama-server -hf bartowski/HemmingwayAI_Hemmingway-1.5-GGUF:Q6_K

Needs a Vulkan build of llama.cpp. Downloads the GGUF on first run.

llama.cpp · Docker with Vulkandocs
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/HemmingwayAI_Hemmingway-1.5-GGUF:Q6_K --host 0.0.0.0 --port 8080 -ngl 99

Server and web UI on port 8080.

LM Studio · Download with the lms CLIdocs
lms get bartowski/HemmingwayAI_Hemmingway-1.5-GGUF@Q6_K

Then load it from the LM Studio app or with `lms load`.

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="HemmingwayAI/Hemmingway-1.5", 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 →
ModelParamsBest quantMemorySpeedLicence
20.9BA4.2BQ8_0≈13 GBFits in memory~126 tok/sCommercial OK
31.2BA4.6BQ5_K_M≈29 GBFits in memory~172 tok/sCommercial OK
32.8BQ6_K≈29 GBFits in memory~21 tok/sCommercial OK
36BA3BQ5_K_M≈26 GBFits in memory~264 tok/sCommercial OK
30.5BA3BQ6_K≈26 GBFits in memory~228 tok/sCommercial OK
24BA2BQ8_0≈26 GBFits in memory~265 tok/sConditions

Other GPUs that run Hemmingway-1.5

Frequently asked questions

Can the Instinct MI50 32GB run Hemmingway-1.5?
Yes. The Instinct MI50 32GB runs Hemmingway-1.5 fully in VRAM at Q6_K (about 26 GB of 32 GB), at roughly 25 tokens/s.
How fast does Hemmingway-1.5 run on the Instinct MI50 32GB?
An estimate from memory bandwidth gives about 25 tokens/s at Q6_K.
Which quantisation of Hemmingway-1.5 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.