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.

summerAIO logo

Can the Instinct MI50 32GB run Qwen3.8-27B-Longbook27-v2?

Qwen3.8-27B-Longbook27-v2·27.1B·Instinct MI50 32GB·32 GB VRAM

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

Yes. The Instinct MI50 32GB runs Qwen3.8-27B-Longbook27-v2 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 Qwen3.8-27B-Longbook27-v2 page →

Every quantisation of Qwen3.8-27B-Longbook27-v2 on the Instinct MI50 32GB

QuantQualityMemoryFitSpeed
Q2_K Heavy loss11 GBfits~63 tok/s
Q3_K_M Noticeable loss15 GBfits~43 tok/s
Q4_K_M Small loss19 GBfits~34 tok/s
Q5_K_M Near-lossless21 GBfits~29 tok/s
Q6_K pickNear-lossless24 GBfits~25 tok/s
Q8_0 Lossless31 GBtight~20 tok/s
FP16 / BF16 Lossless55 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 Qwen3.8-27B-Longbook27-v2 on the Instinct MI50 32GB

Transformers · Chat with the pipeline APIdocs
from transformers import pipeline

pipe = pipeline("text-generation", model="summerAIO/Qwen3.8-27B-Longbook27-v2", 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 Qwen3.8-27B-Longbook27-v2

Frequently asked questions

Can the Instinct MI50 32GB run Qwen3.8-27B-Longbook27-v2?
Yes. The Instinct MI50 32GB runs Qwen3.8-27B-Longbook27-v2 fully in VRAM at Q6_K (about 24 GB of 32 GB), at roughly 25 tokens/s.
How fast does Qwen3.8-27B-Longbook27-v2 run on the Instinct MI50 32GB?
An estimate from memory bandwidth gives about 25 tokens/s at Q6_K.
Which quantisation of Qwen3.8-27B-Longbook27-v2 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.