Intel Arc 140V (16GB)
The Intel Arc 140V (16GB) has 16 GB VRAM and 137 GB/s memory bandwidth. It can run 31 of our 70 tracked models natively in VRAM at 8k context.
Intel Arc 140V (16GB): 2024 Xe2-LPG Battlemage iGPU with 16GB unified LPDDR5X at 137 GB/s — standard Lunar Lake config.
7B at Q8 or 13B at Q4 in unified memory. ~3-5 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 | 16 GB (unified) |
| Memory type | LPDDR5X |
| Memory bandwidth | 137 GB/s |
| Compute backend | VULKAN |
| Tier | Integrated |
| Released | 2024 |
| Models (native) | 31 / 70 |
| Models (offload) | 0 / 70 |
Software: Vulkan backend works in llama.cpp. Shares on-package unified memory with the CPU. Ollama support is limited; SYCL backend available with oneAPI.
Models this GPU runs natively in VRAM (31)
- Qwen3 30B-A3B (MoE)30B · MMLU-Pro 61.5Q2_K · ~152.7 t/s
- Gemma 3 27B Instruct27B · MMLU-Pro 67.5Q2_K · ~15.4 t/s
- Qwen 3.6 27B27B · MMLU-Pro 86.2Q2_K · ~15.4 t/s
- Gemma 4 26B (MoE)26B · MMLU-Pro 82.6Q2_K · ~120.5 t/s
- Mistral Small 3.1 24B Instruct24B · MMLU-Pro 66.8Q2_K · ~17.4 t/s
- Mistral Small 22B22.2B · MMLU-Pro 49.2Q2_K · ~18.8 t/s
- GPT-OSS 20B21B · MMLU-Pro 67.9Q3_K_M · ~87.6 t/s
- Qwen3 14B14.8B · MMLU-Pro 61.0Q4_K_M · ~16.4 t/s
- Qwen 2.5 14B Instruct14.7B · MMLU-Pro 63.7Q4_K_M · ~16.6 t/s
- Phi-4 14B Instruct14B · MMLU-Pro 70.4Q5_K_M · ~15.2 t/s
- Mistral Nemo 12B Instruct12.2B · MMLU-Pro 35.6Q5_K_M · ~17.4 t/s
- Gemma 3 12B Instruct12.2B · MMLU-Pro 60.6Q5_K_M · ~17.4 t/s
- Gemma 2 9B Instruct9.2B · MMLU-Pro 32.0Q6_K · ~18.2 t/s
- Llama 3.1 8B Instruct8B · MMLU-Pro 48.3Q8_0 · ~17.1 t/s
- DeepSeek R1 Distill Llama 8B8B · MMLU-Pro 41.0Q8_0 · ~17.1 t/s
- Qwen3 8B8B · MMLU-Pro 56.7Q8_0 · ~17.1 t/s
- Qwen 2.5 7B Instruct7.6B · MMLU-Pro 56.3Q8_0 · ~18 t/s
- Mistral 7B Instruct v0.37.25B · MMLU-Pro 30.0Q8_0 · ~18.9 t/s
- Gemma 3 4B Instruct4B · MMLU-Pro 43.6BF16 · ~17.1 t/s
- Gemma 4 E4B4B · MMLU-Pro 69.4BF16 · ~17.1 t/s
- Phi-3.5 Mini Instruct3.8B · MMLU-Pro 47.4Q8_0 · ~36.1 t/s
- Llama 3.2 3B Instruct3.2B · MMLU-Pro 24.0BF16 · ~21.4 t/s
- Qwen 2.5 3B Instruct3.1B · MMLU-Pro 32.4BF16 · ~22.1 t/s
- Gemma 2 2B Instruct2.6B · MMLU-Pro 17.8BF16 · ~26.3 t/s
- Gemma 4 E2B2B · MMLU-Pro 60.0FP32 · ~17.1 t/s
- SmolLM2 1.7B Instruct1.7B · MMLU-Pro 19.0FP32 · ~20.1 t/s
- Qwen 2.5 1.5B Instruct1.5B · MMLU-Pro 16.8FP32 · ~22.8 t/s
- Llama 3.2 1B Instruct1.24B · MMLU-Pro 12.5FP32 · ~27.6 t/s
- Gemma 3 1B Instruct1B · MMLU-Pro 14.7FP32 · ~34.3 t/s
- Qwen 2.5 0.5B Instruct0.5B · MMLU-Pro 10.0FP32 · ~68.5 t/s
- SmolLM2 360M Instruct0.36B · MMLU-Pro 8.0FP32 · ~95.1 t/s
Too large for this GPU (39)
- Llama 3.3 70B Instruct
- Qwen 2.5 72B Instruct
- Qwen 2.5 32B Instruct
- Qwen 2.5 Coder 32B Instruct
- Mixtral 8x7B Instruct v0.1
- Gemma 2 27B Instruct
- DeepSeek R1 Distill Llama 70B
- DeepSeek R1 Distill Qwen 32B
- Command-R 35B
- Yi 1.5 34B Chat
- 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)
- Qwen3 32B
- MiniMax M1 456B
- GPT-OSS 120B
- GLM-4.5 355B
- GLM-4.5 Air 106B
- GLM-4.6 355B
- GLM-4.6V 106B
- Nemotron 3 Nano 30B
- GLM-4.7 358B
- Gemma 4 31B
- Qwen 3.5 35B-A3B (MoE)
- Qwen 3.5 122B-A10B (MoE)
- MiniMax M2.5 229B
- GLM-5 744B
- MiniMax M2.7 229B
- Nemotron 3 Super 120B
- Qwen 3.6 35B
- Kimi K2.6
- GLM-5.1 754B
- DeepSeek V4 Pro 1.6T
- DeepSeek V4 Flash 284B
Frequently asked questions
- How much VRAM does the Intel Arc 140V (16GB) have?
- The Intel Arc 140V (16GB) has 16 GB of LPDDR5X with 137 GB/s memory bandwidth (unified system memory, shared between CPU and GPU).
- What is the Intel Arc 140V (16GB) best for?
- With 16 GB of VRAM, the Intel Arc 140V (16GB) handles smaller models (7B–14B) at Q4–Q5 quantization — ideal for entry-level local LLM experimentation and lightweight inference.
- What LLMs can the Intel Arc 140V (16GB) run locally?
- The Intel Arc 140V (16GB) can run 31 of the 70 open-weight models tracked by CanItRun natively in VRAM at 8k context. Top options include: Llama 3.1 8B Instruct at Q8_0, Llama 3.2 3B Instruct at BF16, Llama 3.2 1B Instruct at FP32.
- Can the Intel Arc 140V (16GB) run Llama 3.3 70B Instruct?
- The Intel Arc 140V (16GB) does not have enough VRAM to run Llama 3.3 70B Instruct. You would need more VRAM or a lower quantization level.
- Can the Intel Arc 140V (16GB) run Qwen 3.6 27B?
- Yes. The Intel Arc 140V (16GB) runs Qwen 3.6 27B natively in VRAM at Q2_K quantization, achieving approximately 15.4 tokens per second.
- Can the Intel Arc 140V (16GB) run Llama 3.1 8B Instruct?
- Yes. The Intel Arc 140V (16GB) runs Llama 3.1 8B Instruct natively in VRAM at Q8_0 quantization, achieving approximately 17.1 tokens per second.