Lenovo Yoga Slim 7i Aura (Core Ultra 7 256V)

Scored against every model in our directory at Q4_K_M, using the ~9.6GB of GPU-usable memory on this machine and its 136 GB/s of memory bandwidth. Of 30 models, 6 run comfortably, 2 are a tight fit, and 22 will not load. The largest model that fits well here is Google Gemma 2 9B.

How these are estimated: tokens/sec ≈ memory bandwidth × 0.65 ÷ active weights in GB. These are arithmetic estimates from published specifications, not lab measurements — BFWR does not run a hardware test lab. Real throughput varies with runner, quantization, context length and thermals.

Diffusion models size up differently from language models: the text encoder is often as large as the image model itself, and memory scales with resolution. Measured at 1024×1024, one image at a time, against the ~9.6GB of GPU-usable memory here, 7 of 11 open image models will run — the best being Stable Diffusion 1.5 at BF16 / FP16, peaking near 4.2GB.

Weight sizes are read from the real .safetensors files in each model’s Hugging Face repository. Activation memory is an approximation that varies with the attention implementation and sampler, so leave headroom. These are planning figures, not benchmarks.

What is the largest model the Lenovo Yoga Slim 7i Aura (Core Ultra 7 256V) can run?

Google Gemma 2 9B (9.24B) is the largest model that fits, at roughly 5.8GB in Q4_K_M against ~9.6GB of GPU-usable memory. It is rated "Comfortable" here, with an estimated 15.2 tokens/sec.

How many tokens per second should I expect?

Speed depends on the model, not just the machine. On this hardware the estimates range from about 44.2 tokens/sec for the smallest models down to single digits for the largest that still fit. The estimate uses memory bandwidth (136 GB/s here) × 0.65 ÷ active weights in GB, and is not a measured benchmark.

Can the Lenovo Yoga Slim 7i Aura (Core Ultra 7 256V) run a 70B model?

Not in a usable way. A 70B model needs roughly 40GB+ at Q4_K_M before context, which exceeds the ~9.6GB of GPU-usable memory available here. A mixture-of-experts model is usually the better route on this machine, since only a fraction of its weights are active per token.

How much context can I use?

32k tokens is a sensible ceiling on this machine at Q4_K_M. Context is stored in the KV cache, which grows with every token and competes with the model weights for the same memory, so a longer context means a smaller model.

Can the Lenovo Yoga Slim 7i Aura (Core Ultra 7 256V) generate images with Flux or Stable Diffusion?

Yes. 7 of 11 open image models fit at 1024x1024, the best being Stable Diffusion 1.5 at BF16 / FP16, peaking near 4.2GB. Higher resolutions and larger batches cost proportionally more.

Which runner works best on the Lenovo Yoga Slim 7i Aura (Core Ultra 7 256V)?

Ollama, LM Studio, AnythingLLM are all expected to run on this hardware. Ollama is the simplest starting point, and `ollama run gemma4:12b` is a good first model for this machine.

In-depth reads that pair with this machine — sizing memory, picking a runner, and choosing quantization for ~9.6GB of usable memory.

• How Much RAM and VRAM Do You Need to Run Local LLMs?Model weights, KV cache and OS overhead, tier by tier.Read the guide
• Quantization Guide: Q4_K_M vs Q8_0 vs FP8What each quant level costs you in memory and quality.Read the guide
• Tokens per Second ExplainedWhat sets local LLM speed, and the formula behind our estimates.Read the guide