Can the Instinct MI50 32GB run RWKV7-G1k-13.3B-20260930?
RWKV7-G1k-13.3B-20260930·13.3B·Instinct MI50 32GB·32 GB VRAM
Yes. The Instinct MI50 32GB runs RWKV7-G1k-13.3B-20260930 fully in VRAM at Q8_0 (about 22 GB of 32 GB), at roughly 40 tokens/s.
- best quant
- Q8_0
- needs
- 22 GB
- usable
- 32 GB
- est. speed
- ~40 tok/s
Estimates for an 8K context; offload assumes 32 GB of system RAM.Try other contexts on the RWKV7-G1k-13.3B-20260930 page →
Every quantisation of RWKV7-G1k-13.3B-20260930 on the Instinct MI50 32GB
| Quant | Memory | Fit | Speed |
|---|---|---|---|
| Q2_K | 12 GB | fits | ~129 tok/s |
| Q3_K_M | 14 GB | fits | ~87 tok/s |
| Q4_K_M | 16 GB | fits | ~70 tok/s |
| Q5_K_M | 17 GB | fits | ~60 tok/s |
| Q6_K | 19 GB | fits | ~52 tok/s |
| Q8_0 pick | 22 GB | fits | ~40 tok/s |
| FP16 / BF16 | 34 GB | offload | ~11 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 RWKV7-G1k-13.3B-20260930 on the Instinct MI50 32GB
from transformers import pipeline
pipe = pipeline("text-generation", model="RWKV/RWKV7-G1k-13.3B-20260930", 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 |
|---|---|---|---|---|
| 14.8B | Q8_0 | ≈17 GBFits in memory | ~36 tok/s | |
| 14.7B | Q8_0 | ≈17 GBFits in memory | ~36 tok/s | |
| 20.9BA4.2B | Q8_0 | ≈13 GBFits in memory | ~126 tok/s | |
| 8.2B | Q8_0 | ≈10 GBFits in memory | ~65 tok/s | |
| 8B | Q8_0 | ≈9.8 GBFits in memory | ~66 tok/s | |
| 9.4B | Q8_0 | ≈11 GBFits in memory | ~56 tok/s |
Other GPUs that run RWKV7-G1k-13.3B-20260930
Frequently asked questions
- Can the Instinct MI50 32GB run RWKV7-G1k-13.3B-20260930?
- Yes. The Instinct MI50 32GB runs RWKV7-G1k-13.3B-20260930 fully in VRAM at Q8_0 (about 22 GB of 32 GB), at roughly 40 tokens/s.
- How fast does RWKV7-G1k-13.3B-20260930 run on the Instinct MI50 32GB?
- An estimate from memory bandwidth gives about 40 tokens/s at Q8_0.
- Which quantisation of RWKV7-G1k-13.3B-20260930 should I use on the Instinct MI50 32GB?
- Q8_0: 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.