Intel Arc Pro B50 16GB
16 GB decides what fits. 224 GB/s decides how fast it runs once it does.
Open in the calculator →Best models for 16 GB, on every card that size →
Find one: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
- Largest popular model that fitsgpt-oss-20b21B params · Q4_K_M · needs 13.8 GB~70 tok/s Faster than you readOpen in the calculator →
- Best fast pickERNIE-4.5-21B-A3B-PT22B params · Q4_K_M · needs 14.7 GB~69 tok/s Faster than you readOpen in the calculator →
- Most downloaded that fitsQwen3.5-9B9.7B params · Q4_K_M · needs 7.05 GB~36 tok/s Faster than you readOpen in the calculator →
At 8,192 tokens of context with the whole model in device memory. Speeds are estimates from memory bandwidth, not benchmarks run on this card.
153 of 320 fit entirely
153 of the 320 models the engine can size fit entirely in device memory at Q4_K_M where it is published, otherwise the nearest published format, and 8,192 tokens. 73 run with some layers on system memory (32 GB assumed), and 94 do not run at all.
Featured models · Q4_K_M at 8,192 tokens, including offload
| Model | Needs | Verdict | Decode | Calculator |
|---|---|---|---|---|
| Qwen3.5-2B2.3B parameters | 2.32 GB | fits | ~141 tok/s | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF164.0B parameters | 3.46 GB | fits | ~66 tok/s | Open → |
| Qwen3-VL-8B-Instruct8.8B parameters | 7.04 GB | fits | ~30 tok/sAbout reading pace | Open → |
| Qwen3.5-9B9.7B parameters | 7.05 GB | fits | ~36 tok/s | Open → |
| gemma-4-12B-it12B parameters | 9.54 GB | fits | ~21 tok/sAbout reading pace | Open → |
| gpt-oss-20b21B parameters | 13.8 GB | fits | ~70 tok/s | Open → |
| Qwen3.8-27B28B parameters | 18.6 GB | 10 of 64 layers on system RAM (2.66 GB) | ~9.2 tok/s with offload | Open → |
| Qwen3.6-27B28B parameters | 18.6 GB | 10 of 64 layers on system RAM (2.66 GB) | ~9.2 tok/s with offload | Open → |
| Kimi-Linear-48B-A3B-Instruct49B parameters | 30.4 GB | 14 of 27 layers on system RAM (15.3 GB) | ~48 tok/s with offload | Open → |
| Qwen3.8-Flash-Next180B parameters | 111.6 GB | needs 96.7 GB of system RAM; 32 GB assumed | does not run | Open → |
| DeepSeek-V4-Flash-Vision-Exp305B parameters | 188.1 GB | needs 174.2 GB of system RAM; 32 GB assumed | does not run | Open → |
| GLM-5.3-Flash321B parameters | 198.3 GB | needs 184.1 GB of system RAM; 32 GB assumed | does not run | Open → |
These examples are selected from prominent labs using the catalogue’s latest Hugging Face 30-day downloads and repository-creation freshness signal, with newer releases guaranteed a place. Offloaded rows assume 32 GB of system RAM, and a speed is only shown for a row that runs. Fitting in memory is not the same as loading: whether the runtime and version you have supports each architecture and format on this machine has not been tested here. Each “Open” link carries the same model, format, context and RAM into the calculator.
Fits entirely in Intel Arc Pro B50 16GB memory — 153 of 320 sized models
The most demanding model that fits is gpt-neox-20b at Q4_K_M: 15.7 GB of the 16 GB, leaving 0.25 GB spare.
Fully resident at 8,192 tokens (or the model’s own maximum, where that is shorter), offload off, at 224 GB/s. Each row is a run of the engine for this configuration; the rows start with current, prominent releases and “fits” is memory, not a tested runtime. Older or less prominent models remain available through this search and “Show all”.
Showing 40 of 153 models that fit.
| Model | Format | Needs | Spare | Decode | Downloads / 30d | Calculator |
|---|---|---|---|---|---|---|
| Qwen3.5-9BQwen · 9.7B params | Q4_K_M | 7.05 GB | 8.95 GB | ~36 tok/s | 9M | Open → |
| Qwen3.5-4BQwen · 4.7B params | Q4_K_M | 3.98 GB | 12.0 GB | ~65 tok/s | 7.8M | Open → |
| gemma-4-12B-itGoogle · 12B params | Q4_K_M | 9.54 GB | 6.46 GB | ~21 tok/sAbout reading pace | 1.9M | Open → |
| Qwen3.5-2BQwen · 2.3B params | Q4_K_M | 2.32 GB | 13.7 GB | ~141 tok/s | 4.9M | Open → |
| gemma-4-E4B-itGoogle · 8.0B params | Q4_K_M | 5.86 GB | 10.1 GB | ~58 tok/s | 4.4M | Open → |
| NVIDIA-Nemotron-3-Nano-4B-BF16NVIDIA · 4.0B params | Q4_K_M | 3.46 GB | 12.5 GB | ~66 tok/s | 3.4M | Open → |
| gemma-4-E2B-itGoogle · 5.1B params | Q4_K_M | 4.02 GB | 12.0 GB | ~152 tok/s | 3M | Open → |
| Qwen3.5-0.8BQwen · 873M params | Q4_K_M | 1.46 GB | 14.5 GB | ~310 tok/s | 2.6M | Open → |
| Qwen3-VL-8B-InstructQwen · 8.8B params | Q4_K_M | 7.04 GB | 8.96 GB | ~30 tok/sAbout reading pace | 14.6M | Open → |
| North-Micro-Vision-InstructCohereLabs · 2.5B params | Q4_K_M | 2.99 GB | 13.0 GB | ~93 tok/s | 180.7K | Open → |
| granite-4.2-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 8.51 GB | ~27 tok/sAbout reading pace | 128.4K | Open → |
| granite-4.1-3bIBM · 3.4B params | Q4_K_M | 3.72 GB | 12.3 GB | ~63 tok/s | 521.8K | Open → |
| LFM2.5-2.6BLiquidAI · 2.7B params | Q4_K_M | 2.61 GB | 13.4 GB | ~101 tok/s | 108.1K | Open → |
| Qwen3-VL-4B-InstructQwen · 4.4B params | Q4_K_M | 4.72 GB | 11.3 GB | ~47 tok/s | 3.5M | Open → |
| Qwen3-VL-2B-InstructQwen · 2.1B params | Q4_K_M | 3.05 GB | 13.0 GB | ~85 tok/s | 2.8M | Open → |
| granite-4.2-3bIBM · 3.7B params | Q4_K_M | 3.72 GB | 12.3 GB | ~63 tok/s | 50.6K | Open → |
| LFM2.5-230MLiquidAI · 230M params | Q4_K_M | 1.05 GB | 14.9 GB | ~704 tok/s | 88.6K | Open → |
| Qwen3-0.6BQwen · 752M params | Q4_K_M | 2.22 GB | 13.8 GB | ~131 tok/s | 29.7M | Open → |
| gpt-oss-20bOpenAI · 21B params | Q4_K_M | 13.8 GB | 2.24 GB | ~70 tok/s | 6.6M | Open → |
| granite-4.1-8bIBM · 8.8B params | Q4_K_M | 7.49 GB | 8.51 GB | ~27 tok/sAbout reading pace | 179.3K | Open → |
| LFM2.5-VL-3BLiquidAI · 3.1B params | Q4_K_M | 2.85 GB | 13.1 GB | ~101 tok/s | 26.7K | Open → |
| MiMo-V2.6-Distill-Qwen-9BNEWXiaomiMiMo · 9.4B params | Q4_K_M | 6.90 GB | 9.10 GB | ~36 tok/s | 14.6K | Open → |
| Qwen3-4B-Instruct-2507Qwen · 4.0B params | Q4_K_M | 4.72 GB | 11.3 GB | ~47 tok/s | 3.7M | Open → |
| Ling-3.0-tinyinclusionAI · 7.9B params | Q4_K_M | 5.85 GB | 10.1 GB | ~204 tok/s | 17.7K | Open → |
| Qwen3-8BQwen · 8.2B params | Q4_K_M | 7.04 GB | 8.96 GB | ~30 tok/sAbout reading pace | 10.7M | Open → |
| Olmo-3-7B-Instructallenai · 7.3B params | Q4_K_M | 7.96 GB | 8.04 GB | ~25 tok/sAbout reading pace | 481.7K | Open → |
| Qwen3-4BQwen · 4.0B params | Q4_K_M | 4.51 GB | 11.5 GB | ~47 tok/s | 7.8M | Open → |
| LFM2.5-8B-A1BLiquidAI · 8.5B params | Q4_K_M | 6.06 GB | 9.94 GB | ~157 tok/s | 32.4K | Open → |
| LFM2.5-350MLiquidAI · 354M params | Q4_K_M | 1.13 GB | 14.9 GB | ~455 tok/s | 69.9K | Open → |
| Hy-MT2-1.8BTencent · 2.0B params | Q4_K_M | 2.47 GB | 13.5 GB | ~105 tok/s | 28.9K | Open → |
| LLaDA2.0-miniinclusionAI · 16B params | Q4_K_M | 11.0 GB | 5.00 GB | ~163 tok/s | 217.2K | Open → |
| LFM2.5-1.2B-InstructLiquidAI · 1.2B params | Q4_K_M | 1.63 GB | 14.4 GB | ~168 tok/s | 119.2K | Open → |
| Ministral-3-14B-Instruct-2512Mistral AI · 14B params | Q4_K_M | 10.4 GB | 5.62 GB | ~19 tok/sAbout reading pace | 251K | Open → |
| Qwen3-1.7BQwen · 2.0B params | Q4_K_M | 3.02 GB | 13.0 GB | ~85 tok/s | 3.1M | Open → |
| Nemotron-3.5-Content-SafetyNVIDIA · 4.3B params | Q4_K_M | 3.73 GB | 12.3 GB | ~63 tok/s | 14.1K | Open → |
| Hy-MT2-7BTencent · 8.0B params | Q4_K_M | 6.50 GB | 9.50 GB | ~31 tok/s | 15.4K | Open → |
| Qwen3-14BQwen · 15B params | Q4_K_M | 11.1 GB | 4.86 GB | ~18 tok/sAbout reading pace | 2.7M | Open → |
| GLM-4.6V-Flashzai-org · 10B params | Q4_K_M | 7.45 GB | 8.55 GB | ~30 tok/s | 103.7K | Open → |
| Qwen2.5-VL-7B-InstructQwen · 8.3B params | Q4_K_M | 6.36 GB | 9.64 GB | ~36 tok/s | 5.8M | Open → |
| SmolLM3-3BHuggingFaceTB · 3.1B params | Q4_K_M | 3.46 GB | 12.5 GB | ~69 tok/s | 617K | Open → |
Sized at the format most people actually download, not at FP16. The catalogue ordered by downloads →
Find the Intel Arc Pro B50 16GB: Amazon ↗ · eBay (new and used) ↗Store links may pay us a commission. They never decide which card is suggested — the memory arithmetic does.
The Intel Arc Pro B50 16GB, model by model
One page per model: whether it fits this device, at which formats, and how fast.
The specification behind every figure
What the manufacturer publishes for this device, and the pages it was read from.
Manufacturer specification
| Memory scope | dedicated |
|---|---|
| Capacity | 16 GB |
| Published options | 16 GB |
| Bandwidth | 224 GB/s |
| Memory type | GDDR6 |
| Bus width | 128-bit |
| FP32 peak | Not published |
| Dense matrix peak | Not published without sparsity |
| Total board power | 70 W |
Source ledger
Caveats
- Intel publishes peak INT8 throughput for this card rather than a dense half-precision matrix figure, so no compute roof is priced for it and time to first token is withheld rather than estimated.
- Local inference on Intel graphics runs through SYCL or Vulkan backends whose overhead this engine has not calibrated separately; the memory arithmetic is unaffected, the speed estimate is the generic one.
- The Intel specification page moved from SKU 242614 (HTTP 404 on 2026-09-13, audit H02) to SKU 242615; the figures were re-read there on 2026-09-13 and are unchanged.
Published capacity is a hardware ceiling, not guaranteed free runtime memory. The calculator shows the runtime reserve separately rather than folding it into a single number.
Run the diagnostic on the Intel Arc Pro B50 16GB →