Intel Arc 140V (32GB)
The Intel Arc 140V (32GB) has 32 GB VRAM and 137 GB/s memory bandwidth. It can run 52 of our 94 tracked models natively in VRAM at 8k context.
With 32 GB LPDDR5X, the Intel Arc 140V (32GB) is a integrated-tier GPU that can run 52 models natively. It comfortably runs 7B–32B models at Q4; 70B-class models typically need CPU offload.
The Intel Arc 140V is the flagship Lunar Lake integrated GPU, built on the Xe2 (Battlemage) architecture and sharing 32GB of on-package LPDDR5X with the Core Ultra 200V CPU. At 137 GB/s it's bandwidth-constrained compared to discrete cards, but the 32GB unified pool lets it load 13B models at Q8 or 30B models at Q4, making it one of the most capable laptop iGPUs for local LLM inference.
Intel Arc 140V (32GB): 2024 Xe2-LPG Battlemage iGPU with 32GB unified LPDDR5X at 137 GB/s, top Lunar Lake AI laptop iGPU.
13B at Q8 or 30B at Q4 in unified memory. ~3-6 t/s for 7B via Vulkan; bandwidth-constrained.
Vulkan via llama.cpp works; shares on-package memory with CPU. SYCL backend available with oneAPI. Ollama support limited.
| Vendor | Intel |
| Architecture | Xe2-LPG (Battlemage) |
| VRAM | 32 GB (unified) |
| Memory type | LPDDR5X |
| Memory bandwidth | 137 GB/s |
| Compute backend | VULKAN |
| Tier | Integrated |
| Released | 2024 |
| Models (native) | 52 / 94 |
| Models (offload) | 0 / 94 |
Software: Vulkan backend works in llama.cpp. Shares on-package unified memory with the CPU. Ollama support is limited; SYCL backend available with oneAPI.
Popular models for this GPU
Models this GPU runs natively in VRAM (52)
- Mixtral 8x7B Instruct v0.146.7B · MMLU-Pro 29.7Q2_K · ~5.1 t/s
- Qwen 3.5 35B-A3B (MoE)35B · MMLU-Pro 85.3Q3_K_M · ~17.9 t/s
- Qwen 3.6 35B35B · MMLU-Pro 85.2Q3_K_M · ~4.7 t/s
- Ornith 1.5 35B-A3B (MoE)35B · MMLU-Pro N/AQ3_K_M · ~17.9 t/s
- Yi 1.5 34B Chat34.4B · MMLU-Pro 37.0Q3_K_M · ~4.8 t/s
Show 47 more
- Qwen3 32B32.8B · MMLU-Pro 65.5Q4_K_M · ~4.2 t/s
- Qwen 2.5 32B Instruct32.5B · MMLU-Pro 69.0Q3_K_M · ~5 t/s
- Qwen 2.5 Coder 32B Instruct32.5B · MMLU-Pro 62.3Q3_K_M · ~5 t/s
- DeepSeek R1 Distill Qwen 32B32.5B · MMLU-Pro 65.0Q3_K_M · ~5 t/s
- Nemotron 3 Nano 30B32B · MMLU-Pro 78.3Q4_K_M · ~13.6 t/s
- Gemma 4 31B30.7B · MMLU-Pro 85.2Q4_K_M · ~4.4 t/s
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q4_K_M · ~12.9 t/s
- Nemotron 3.5 Lightning 30B-A3B30B · MMLU-Pro 81.6Q5_K_M · ~12.4 t/s
- Muse Glimmer 30B27.8B · MMLU-Pro N/AQ5_K_M · ~4.5 t/s
- Gemma 2 27B Instruct27.2B · MMLU-Pro 38.0Q4_K_M · ~4.5 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q5_K_M · ~4.3 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q5_K_M · ~4.5 t/s
- UI-Mate 27B27B · MMLU-Pro ~86.2Q5_K_M · ~4.5 t/s
- Bonsai 27B27B · MMLU-Pro 81.5Ternary (Q2_0) · ~10.1 t/s
- Qwen 3.8 27B27B · MMLU-Pro N/AQ5_K_M · ~4.5 t/s
- Gemma 4 26B (MoE)25.2B · MMLU-Pro 82.6Q6_K · ~8.3 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q6_K · ~4.2 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q6_K · ~4.4 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q6_K · ~8.9 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0Q8_0 · ~5.2 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7Q8_0 · ~5.2 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4Q8_0 · ~5.5 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6Q8_0 · ~6.2 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6Q8_0 · ~6.3 t/s
- Gemma 4 12B (Unified)12B · MMLU-Pro 77.2Q8_0 · ~5.6 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0BF16 · ~4.2 t/s
- Qwen 3.5 9B9B · MMLU-Pro 82.5BF16 · ~4.9 t/s
- Ornith 1.5 9B9B · MMLU-Pro N/ABF16 · ~4.9 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3BF16 · ~5.2 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0BF16 · ~5.2 t/s
- Qwen3 8B8B · MMLU-Pro 56.7BF16 · ~5.2 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3BF16 · ~5.7 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0BF16 · ~5.7 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6FP32 · ~5.4 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4FP32 · ~5.2 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4FP32 · ~4.8 t/s
- Phi-4-mini Instruct3.8B · MMLU-Pro 67.3FP32 · ~5.5 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0FP32 · ~6.5 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4FP32 · ~7 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8FP32 · ~7.9 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~10.6 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~10.6 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~14.3 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~17 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~20.6 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~42.4 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~50.2 t/s
Too large for this GPU (42)
- Llama 3.3 70B Instruct
- Qwen 2.5 72B Instruct
- DeepSeek R1 Distill Llama 70B
- Command-R 35B
- Llama 3.1 70B Instruct
- Mixtral 8x22B Instruct v0.1
- Llama 3.1 405B Instruct
- DeepSeek V3 671B
- DeepSeek R1 671B
- Llama 4 Scout 109B
- Llama 4 Maverick 400B
- Qwen3 235B-A22B (MoE)
- MiniMax M1 456B
- GPT-OSS 120B
- GLM-4.5 355B
- GLM-4.5 Air 106B
- GLM-4.6 355B
- GLM-4.6V 106B
- GLM-4.7 358B
- Qwen 3.5 122B-A10B (MoE)
- MiniMax M2.5 229B
- GLM-5 744B
- MiniMax M2.7 229B
- Nemotron 3 Super 120B
- Kimi K2.6
- GLM-5.1 754B
- DeepSeek V4 Pro 1.6T
- DeepSeek V4 Flash 284B
- Mistral Medium 3.5 128B
- GLM-5.2 753B
- Nemotron 3 Ultra 550B-A55B
- Step 3.5 Flash
- Step 3.7 Flash
- MiMo V2.5 Pro
- Kimi K2.5
- MiniMax M3
- Inkling
- Kimi K3
- DeepSeek V4 Flash 0731 284B
- Qwen3.8 2.4T-A95B
- DeepSeek V4 Pro 0813 1.6T
- Ornith 1.5 397B (MoE)
Frequently asked questions
- How much VRAM does the Intel Arc 140V (32GB) have?
- The Intel Arc 140V (32GB) has 32 GB of LPDDR5X with 137 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
- What is the Intel Arc 140V (32GB) best for?
- With 32 GB of VRAM, the Intel Arc 140V (32GB) is well-suited for running 7B–32B models at Q4 with room for context, making it a great all-rounder for local LLM inference.
- What LLMs can the Intel Arc 140V (32GB) run locally?
- The Intel Arc 140V (32GB) can run 52 of the 94 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Qwen 3.8 27B at Q5_K_M, Muse Glimmer 30B at Q5_K_M, Ornith 1.5 9B at BF16.
- Can the Intel Arc 140V (32GB) run Gemma 4 31B?
- Yes. The Intel Arc 140V (32GB) runs Gemma 4 31B natively in VRAM at Q4_K_M quantization, achieving approximately 4.4 tokens per second.
- Can the Intel Arc 140V (32GB) run Qwen 3.6 27B?
- Yes. The Intel Arc 140V (32GB) runs Qwen 3.6 27B natively in VRAM at Q5_K_M quantization, achieving approximately 4.5 tokens per second.
- Can the Intel Arc 140V (32GB) run Qwen3 8B?
- Yes. The Intel Arc 140V (32GB) runs Qwen3 8B natively in VRAM at BF16 quantization, achieving approximately 5.2 tokens per second.