01.AI on AMD RDNA3

Can I run Yi-1.5 34B on an Radeon RX 7900 XTX?

Not at Q4_K_M — it needs 22.2 GB against 21.8 GB available. Drop to Q4_K_S and it fits, at about 27.9 tokens per second.

Won't fit

22.2 GB of 21.8 GB · 102%
023 GB
Weights 19.5 GB
KV cache 1.9 GB
Runtime overhead 0.9 GB
Over the limit 0.5 GB

Short by 0.5 GB. You can run it with 58 of 60 layers on the Radeon RX 7900 XTX and the rest in system RAM, at roughly 18.1 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation18.1tok/s
Prompt processing751tok/s
Max context6Ktokens
KV per 1K tokens0GB

Every quantisation of Yi-1.5 34B on a Radeon RX 7900 XTX

Highlighted row is the highest quality that still fits at 8K context.

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 64.1 GB 66.8 GB Won't fit — 0.76
INT8 / W8A8 8.50 33.8 GB 36.6 GB Won't fit — 2.15
Q8_0 (GGUF) 8.50 33.8 GB 36.6 GB Won't fit — 2.15
FP8 (E4M3) 8.00 32.0 GB 34.8 GB Won't fit — 2.42
Q6_K 6.56 26.3 GB 29.0 GB Won't fit — 4.03
Q5_K_M 5.67 22.7 GB 25.5 GB Won't fit — 6.90
Q5_K_S 5.52 22.1 GB 24.9 GB Won't fit — 7.61
Q4_K_M 4.85 19.5 GB 22.2 GB Won't fit 6K 18.1
Q4_K_S 4.58 18.4 GB 21.2 GB Fits, but tight 10K 27.9
Q4_0 4.55 18.3 GB 21.1 GB Fits, but tight 11K 28.1
AWQ 4-bit 4.25 18.3 GB 21.0 GB Fits, but tight 11K 28.1
GPTQ 4-bit 4.25 18.3 GB 21.0 GB Fits, but tight 11K 28.1
MXFP4 4.25 18.3 GB 21.0 GB Fits, but tight 11K 28.1
IQ4_XS 4.25 17.2 GB 19.9 GB Fits, but tight 16K 29.9
Q3_K_M 3.91 15.8 GB 18.6 GB Runs comfortably 22K 32.2
IQ3_M 3.70 15.0 GB 17.8 GB Runs comfortably 25K 33.8
IQ3_XXS 3.06 12.5 GB 15.3 GB Runs comfortably 32K 40.0
Q2_K 2.63 10.8 GB 13.6 GB Runs comfortably 32K 45.6
IQ2_XXS 2.06 8.6 GB 11.4 GB Runs comfortably 32K 56.0
IQ1_M 1.75 7.4 GB 10.2 GB Runs comfortably 32K 63.9

Also worth checking

Yi-1.5 34B on every GPU
Full hardware tableEverything that runs on a Radeon RX 7900 XTX
Full model tableWhy the KV cache is the part that bites
Guide