Local model performance on your hardware

Find which open-weight LLMs fit in your GPU or Mac and compare the speeds people report on setups like yours.

What runs on your hardware?

Pick your GPU or Mac, then read the speeds people reported on it, or estimate which models fit and how fast they run.

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Looking for a particular model?

Search for a model to see its reported speeds across GPUs and Macs.

Local model performance reports from the community

These are individual setups, not a controlled benchmark. Compare GPU count, quantization, context and offloading before comparing speeds. How to read a report →

Model: MiniCPM-V 4.7

Compare setup details

QuantizationEngineRecorded GPU countReported context (tokens)

Exact recorded values. Context may be a configured limit; matching filters does not establish identical prompts, offloading or concurrency.

MiniCPM-V 4.7 35B (3B active)

Unknown GPU

generation:: 13.0 tokens/s

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is shown only when the source reports it; generation speed cannot tell us time to first token. Check the full setup before comparing.

visionlong-context

User reports MiniCPM-V 4.7, a 35B-A3B MoE vision model, running at 13+ tok/s on an iPhone 17 Pro Max with a 3GB inference memory footprint. Experts are streamed from flash storage using Lookahead Expert Scheduling (LES), which predicts upcoming expert needs and overlaps loading with computation. The 3GB figure is the inference memory footprint; the app README lists a ~16.6GB download and recommends at least 12GB of device RAM. A smaller 1B version exists, and code and weights are Apache 2.0.

Showing 1–1 of 1

Page 1 of 1

Community benchmarks snapshot

Records by GPU

AMD Strix Halo 128GB298NVIDIA RTX 3090191NVIDIA RTX 5090138NVIDIA DGX Spark79M5 Max 48GB66NVIDIA RTX Pro 6000 Blackwell63NVIDIA RTX 5060 Ti 16GB59NVIDIA RTX 3060 12GB54AMD Radeon AI PRO R9700 32GB52M4 Max 128GB49

Records by model

Qwen3.81055

Qwen3.6240

Gemma 4154

DeepSeek V4 Flash147

Qwen3.5100

Qwen354

other533

Records by engine

llama.cpp900

vLLM189

MLX102

Strata83

Ollama65

other359

Use cases

coding 577agentic 369long-context 281tool-use 157vision 113summarization 54math 43creative-writing 39multilingual 25text-generation 9rp 8reasoning 3

coding577agentic369long-context281tool-use157vision113summarization54math43creative-writing39

Median generation t/s by GPU

On Qwen3.8 27B at 4-bit, plain single-GPU runs. Full ranking

RTX 509082RTX Pro 600067M5 Ultra 256GB50RX 7900 XTX48RTX 309036RX 7800 XT 16GB35RTX 5090 Laptop 24GB34RTX 409032V100 32GB31Radeon AI PRO R9700 32GB30

Prompt processing, same model

M5 Ultra 256GB1800RX 7900 XTX530RTX 3090561RTX 40901949V100 32GB941RTX 3080 20GB997Arc Pro B70512M1 Ultra 128GB153Arc Pro B60 24GB380M1 Max 32GB82

Reports by model size

Qwen3.8 27B579Qwen3.8 125B · 6B active392Qwen3.6 35B · 3B active131DeepSeek V4 Flash 284B · 13B active130Qwen3.6 27B72Gemma 4 26B · 4B active37GLM-5.3 320B · 18B active35DeepSeek V4.1 Flash 552B · 16B active29

Quants

Q4_K_M301UD-Q4_K_XL144NVFP4123Q8_0994-bit83Q4_K_XL71IQ4_XS71MXFP458IQ3_XXS56Q450