llamaperf

Intel Arc Pro B60 24GB

INTEL · 24GB · 9 reports

Is this your card?

On the Intel Arc Pro B60 24GB, Qwen3.8 27B at 4-bit, the model most run on it, generates a median of 18.8 tokens per second from 4 plain runs (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, the models most run on the Intel Arc Pro B60 24GB, each one size at one quant level, with the median generation speed of its plain runs (one device, one request, no speculative decoding):

Bars are medians on one scale, 0 to 22.2 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Engines people use on it: llama.cpp 8 (reports)

Run models on your Intel Arc Pro B60 24GB? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance on the Intel Arc Pro B60 24GB

These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 24 GB of VRAM. Prompt processing is how fast the input is read, not how long you wait for the first word. How to measure time to first token.

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Tone: negativeIntel hardware
generation:
15.6 tokens/s
prompt processing (prefill):
339.4 tokens/s
quant:
Q4_K_M (GGUF)

User compares Qwen3.8-27B Q4_K_M on an Intel Arc Pro B60 24GB under WSL2 with Mesa Dozen against the native Windows Vulkan build of llama.cpp b11889. Native Windows gives 339.4 t/s prompt and 15.6 t/s generation with -ngl 99; the WSL2 run segfaults during generation after 49.9 t/s prompt. The crash is in libLLVM-14.so from Intel's Windows driver package, at the same offset across four crashes, two quants and both llama-bench and llama-cli. It runs at -ngl 0 or 1 and crashes from -ngl 2 up, with 23.6 GiB VRAM free. Other models on the same card are 8 to 40 times slower under WSL2: Ornith 1.5 9B Q8_0 at 141.7 / 4.1 versus 975.8 / 36.2, and Qwen3-Coder-30B-A3B Q4_K_M at 34 / 2.5 versus 788.8 / 99.2. Dozen reports matrix cores none and a non-conformant Vulkan warning, while native Windows reports KHR_coopmat.

Oct 30, 2026

Qwen3.8 27B

Intel Arc Pro B60 24GB · llama.cpp · 65,536 ctx

Tone: positiveIntel hardware
generation:
53.0 tokens/s
kv:
f16
coding

User reports Qwen3.8-27B at 53 tok/s mean decode on an Intel Arc Pro B60 24GB, with a 64K context window. Setup is llama.cpp on the Vulkan backend with f16 KV cache, -ub 256 and a q8 draft KV cache, using DFlash2 speculative decoding and Intel's FA prefill kernel. Driver 32.0.101.8976 on Windows 11. The user notes smaller cards (B580/B570/B50/A770) will not fit this 27B, though the Vulkan tuning applies. The same card also runs LTX-2.5 video generation via ComfyUI on XPU.

Oct 17, 2026

Qwen3.8 27B

Intel Arc Pro B60 24GB · llama.cpp · 32,768 ctx

Tone: positiveIntel hardware
generation:
53.3 tokens/s
prompt processing (prefill):
420.0 tokens/s
quant:
Q4_K_M (GGUF)
kv:
F16
codingagentic

User reports Qwen3.8-27B at 53.3 tok/s per-request decode (47 to 58 across eight requests) on an Intel Arc Pro B60 24GB. Setup is llama.cpp Vulkan build b11524 with Q4_K_M and an F16 KV cache, a DFlash2 draft model, one request at a time, 32K context, the whole model on the card. The repo's 42.3 tok/s headline is wall-clock eval-suite throughput with prompt processing included, not a decode rate; stock llama.cpp with no drafter gave 16 tok/s in llama-bench tg32. Prompt reading at 32K was 420 tok/s with the Intel FA kernel, versus 118 tok/s stock.

Oct 11, 2026

Qwen3.8 27B

Intel Arc Pro B60 24GB · intel-llm-scaler · 95,000 ctx

Tone: positiveIntel hardware
generation:
22.0 tokens/s
quant:
INT4
coding

User reports Qwen3.8-27B at a stable 22 t/s generation with up to 95k context on an Intel Arc Pro B60 24GB connected via Oculink to a GMKTEC M7 Pro with 32 GB RAM. Setup is intel-llm-scaler with an INT4 quant. The user also tried a Swift-Qwen3.8 fine-tune and MTP, but MTP limited context to about 50k and produced garbage quickly. llama.cpp was slower than vLLM on both Vulkan and SYCL. User asks whether better options exist for a 24 GB card than Qwen3.8-27B, mentioning Qwen3.8-Next-Flash as likely too heavy.

Oct 8, 2026
Tone: positiveIntel hardware
generation:
91.9 tokens/s
prompt processing (prefill):
1760.0 tokens/s
quant:
Q4_0 (GGUF)
agenticcoding

User reports Nemotron 3.5 Lightning 30B-A3B at 91.91 tok/s decode on 2x Intel Arc Pro B60 24GB. Setup is llama.cpp SYCL with Q4_0 weights and an MTP Q8_0 drafter at --spec-draft-n-max 7, 22.18 GiB VRAM, 1,760 tok/s prefill at 12K context. MTP acceptance is 99.5-100% at every n-max; the model needs the whole card with no co-residence.

Oct 3, 2026

Qwen3.8 27B

Intel Arc Pro B60 24GB · llama.cpp · 512 ctx

Intel hardware
generation:
15.3 tokens/s
prompt processing (prefill):
513.4 tokens/s
quant:
Q4_K_M (GGUF)
kv:
Q8_0

User benchmarks Qwen3.8-27B at 15.34 t/s generation and 513.39 t/s prompt processing on a single Intel Arc Pro B60. Setup is llama.cpp build b10452 with Vulkan backend, Q4_K_M GGUF weights and Q8_0 KV cache, full GPU offload with Flash Attention, at 512 tokens of context. A second run on two Arc Pro B60 cards gives 14.99 t/s decode and 507.93 t/s prefill at 512 tokens; dual-card prefill scales to 643.16 t/s at 1k, 718.37 t/s at 2k and 149.30 t/s at 64k, while decode stays near 15 t/s.

Oct 3, 2026

Qwen3.8 27B Swift

2× Intel Arc Pro B60 24GB · llama.cpp · 131,072 ctx

Tone: positiveIntel hardware
generation:
24.0 tokens/s
prompt processing (prefill):
609.5 tokens/s
quant:
Q4_K_M (GGUF)
kv:
Q8_0

User reports Qwen3.8-27B at 24.00 tok/s decode on dual Intel Arc Pro B60 24GB (48GB total). Setup is llama.cpp build b11100 with SYCL F16 JIT, Q4_K_M GGUF, Q8_0 KV cache, 131072 context, and native embedded Q8_0 MTP draft speculative decoding. Prefill is 609.47 tok/s at 512 tokens, scaling to 925.39 tok/s at 4k and 570.24 tok/s at 128k. Stock non-MTP decode is 16.13 tok/s; live llama-server chat with MTP ranges 20.00-30.29 tok/s.

Oct 3, 2026
Tone: mixedIntel hardware
generation:
8.3 tokens/s
prompt processing (prefill):
112.6 tokens/s
quant:
Q4_K_XL (GGUF)

User benchmarks Qwen3.5 35B-A3B at 8.34 t/s generation and 112.62 t/s prompt processing on an Intel Arc Pro B60 24GB. Setup is llama.cpp build 8175 with the SYCL backend, Q4_K_XL GGUF weights, full GPU offload (-ngl 100). User reports the card is ok for chat-length context on smaller models but slow for agentic tools like opencode/claude code, where initial prompt response can take 5-10 minutes. A comparison run of the same model on an RTX Pro 4500 Blackwell reached 133.47 t/s generation and 3807.62 t/s prompt processing.

Oct 3, 2026

Qwen3.8 27B

Intel Arc Pro B60 24GB · llama.cpp · 150,000 ctx

Tone: positiveIntel hardware
generation:
22.2 tokens/s
prompt processing (prefill):
245.5 tokens/s
quant:
Q4_K (GGUF)
codingmathlong-context

User benchmarks a Qwen3.8-27B Ridge Intel Arc tuned GGUF on an Intel Arc Pro B60 24GB, reporting 22.23 tok/s pure autoregressive decode and 245.54 tok/s prompt prefill. Setup is llama.cpp with Q4_K weights, -ngl 99 and -fa on, on a single 24GB card. With embedded MTP speculative decoding the tuned Ridge build reaches 41.28 tok/s at 93.4% acceptance, and the DAS Lab IQ3_S tuned build reaches 41.88 tok/s at 92.9% acceptance. Stock IQ3_XXS decodes at 8.10 tok/s and stock Unsloth UD-Q4_K_S at 12.97 tok/s. At ~150k-token depth decode falls to 7.91 tok/s with DFlash2 and 7.21 tok/s with native MTP.

Sep 26, 2026

Get a weekly email of new Intel Arc Pro B60 24GB reports and newly released models that fit it.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
Qwen3.8 27B
Intel Arc Pro B60 24GB
Q4_K_M
llama.cpp
Not reported15.6 tokens/s
Qwen3.8 27B
Intel Arc Pro B60 24GB
Not reported
llama.cpp
65,53653.0 tokens/s
Qwen3.8 27B
Intel Arc Pro B60 24GB
Q4_K_M
llama.cpp
32,76853.3 tokens/s
Qwen3.8 27B
Intel Arc Pro B60 24GB
INT4
intel-llm-scaler
95,00022.0 tokens/s
Nemotron 3.5 Lightning 30B (3B active)
2× Intel Arc Pro B60 24GB
Q4_0
llama.cpp
Not reported91.9 tokens/s
Qwen3.8 27B
Intel Arc Pro B60 24GB
Q4_K_M
llama.cpp
51215.3 tokens/s

Frequently asked

How fast is the Intel Arc Pro B60 24GB for local LLMs?

On the Intel Arc Pro B60 24GB, Qwen3.8 27B at 4-bit, the model most run on it, generates a median of 18.8 tokens per second from 4 plain runs (community reports, as of 22 Nov 2026). Also reported: Qwen3.5 35B · 3B active at 4-bit (8.3 t/s, one plain run).

What is the biggest model reported running on the Intel Arc Pro B60 24GB?

The largest model with a plain generation run on the Intel Arc Pro B60 24GB is Qwen3.5 35B · 3B active at 4-bit (8.3 t/s, one plain run), as of 22 Nov 2026. Plain means one device, one request, no speculative decoding, so a run split across several cards does not count.