OpenAI on Intel Battlemage

Can I run gpt-oss 20B-A3.6B on an Arc B580?

Not at Q4_K_M — it needs 13.1 GB against 10.5 GB available. Drop to IQ3_M and it fits, at about 100 tokens per second.

Won't fit

13.1 GB of 10.5 GB · 125%
014 GB
Weights 11.9 GB
KV cache 0.4 GB
Runtime overhead 0.8 GB
Over the limit 2.6 GB

Short by 2.6 GB. You can run it with 18 of 24 layers on the Arc B580 and the rest in system RAM, at roughly 37.5 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.

Generation37.5tok/s
Prompt processing2683tok/s
Max context0tokens
KV per 1K tokens0GB

Every quantisation of gpt-oss 20B-A3.6B on a Arc B580

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

QuantisationbpwWeights TotalVerdictMax ctxtok/s
FP16 / BF16 16.00 38.9 GB 40.1 GB Won't fit — 5.66
INT8 / W8A8 8.50 20.4 GB 21.6 GB Won't fit — 13.3
FP8 (E4M3) 8.00 19.5 GB 20.6 GB Won't fit — 14.6
Q6_K 6.56 16.0 GB 17.1 GB Won't fit — 19.8
Q5_K_M 5.67 13.8 GB 15.0 GB Won't fit — 27.8
Q5_K_S 5.52 13.4 GB 14.6 GB Won't fit — 28.5
AWQ 4-bit 4.25 11.9 GB 13.1 GB Won't fit — 37.4
GPTQ 4-bit 4.25 11.9 GB 13.1 GB Won't fit — 37.4
MXFP4 4.25 11.9 GB 13.1 GB Won't fit — 37.4
Q4_K_M 4.85 11.9 GB 13.1 GB Won't fit — 37.5
Q4_K_S 4.58 11.3 GB 12.4 GB Won't fit — 43.2
Q4_0 4.55 11.2 GB 12.4 GB Won't fit — 43.4
IQ4_XS 4.25 10.5 GB 11.7 GB Won't fit — 57.1
Q3_K_M 3.91 9.7 GB 10.9 GB Won't fit — 69.5
IQ3_M 3.70 9.2 GB 10.4 GB Fits, but tight 9K 100
IQ3_XXS 3.06 7.8 GB 8.9 GB Runs comfortably 41K 115
Q2_K 2.63 6.8 GB 8.0 GB Runs comfortably 62K 128
IQ2_XXS 2.06 5.5 GB 6.7 GB Runs comfortably 90K 149
IQ1_M 1.75 4.8 GB 5.9 GB Runs comfortably 105K 164

Also worth checking

gpt-oss 20B-A3.6B on every GPU
Full hardware tableEverything that runs on a Arc B580
Full model tableWhy the KV cache is the part that bites
Guide