RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can I run KORMo Web 11B on my PC?

New release: KORMo Web 11B was published on Hugging Face on Nov 14, 2026 by KORMo-VL. Numbers update hourly as GGUF files appear. See everything new this week.

KORMo Web 11B (11B) needs about 8.3 GB of GPU memory at 4-bit with an 8K context. The cheapest consumer GPU in our table that runs it fully in VRAM at 4-bit or better is the Arc B580 (12 GB, $249 launch MSRP). With llama.cpp offload, the smallest card that can run it is the RX 7600 with 32 GB of system RAM, at an estimated 12.5–18.9 tokens/sec (usable for chat). The smallest Mac that runs it is the Mac M4 16GB.

8.3 GBneeded at 4-bit, 8K
47GPUs/Macs: fully in memory
6GPUs: with CPU offload
M4 16GBsmallest Mac

KORMo Web 11B on every GPU and Mac

Best quant that fits fully in memory at 8K context with a speed ceiling; otherwise the llama.cpp offload plan (system RAM needed, estimated speed from DDR4-3200 to DDR5-6000). Macs and unified-memory PCs share one pool, so offload adds nothing there. How offload is estimated.

HardwareMemoryVerdictDetails
RX 76008 GBOffload Q4_K_M, 32 GB RAM · ~13–19 tok/sdetails
RTX 40608 GBOffload Q4_K_M, 32 GB RAM · ~12–18 tok/sdetails
RTX 50608 GBOffload Q4_K_M, 32 GB RAM · ~14–23 tok/sdetails
RTX 3060 Ti8 GBOffload Q4_K_M, 32 GB RAM · ~14–23 tok/sdetails
RTX 4060 Ti 8GB8 GBOffload Q4_K_M, 32 GB RAM · ~13–19 tok/sdetails
RTX 30708 GBOffload Q4_K_M, 32 GB RAM · ~14–23 tok/sdetails
RTX 3080 10GB10 GBQ4_K_M · ~111 tok/sdetails
Arc B58012 GBQ5_K_M · ~57 tok/sdetails
RTX 3060 12GB12 GBQ5_K_M · ~45 tok/sdetails
RX 7700 XT12 GBQ5_K_M · ~54 tok/sdetails
RTX 507012 GBQ5_K_M · ~84 tok/sdetails
RTX 407012 GBQ5_K_M · ~63 tok/sdetails
RTX 4070 Super12 GBQ5_K_M · ~63 tok/sdetails
RTX 4070 Ti12 GBQ5_K_M · ~63 tok/sdetails
RTX 3080 12GB12 GBQ5_K_M · ~114 tok/sdetails
Arc A770 16GB16 GBQ8_0 · ~47 tok/sdetails
RTX 5060 Ti 16GB16 GBQ8_0 · ~38 tok/sdetails
RTX 4060 Ti 16GB16 GBQ8_0 · ~24 tok/sdetails
RX 7800 XT16 GBQ8_0 · ~52 tok/sdetails
RX 7900 GRE16 GBQ8_0 · ~48 tok/sdetails
RX 907016 GBQ8_0 · ~54 tok/sdetails
RX 9070 XT16 GBQ8_0 · ~54 tok/sdetails
RTX 5070 Ti16 GBQ8_0 · ~75 tok/sdetails
RTX 4070 Ti Super16 GBQ8_0 · ~57 tok/sdetails
RTX 4080 Super16 GBQ8_0 · ~62 tok/sdetails
RTX 508016 GBQ8_0 · ~81 tok/sdetails
RTX 408016 GBQ8_0 · ~60 tok/sdetails
RX 7900 XT20 GBQ8_0 · ~67 tok/sdetails
RX 7900 XTX24 GBQ8_0 · ~81 tok/sdetails
RTX 309024 GBQ8_0 · ~79 tok/sdetails
RTX 409024 GBQ8_0 · ~85 tok/sdetails
RTX 3090 Ti24 GBQ8_0 · ~85 tok/sdetails
RTX 509032 GBF16 · ~80 tok/sdetails
DGX Spark128 GBF16 · ~12 tok/sdetails
Ryzen AI Max+ 395 128GB128 GBF16 · ~11 tok/sdetails
Mac M1 16GB16 GBQ5_K_M · ~9 tok/sdetails
Mac M4 16GB16 GBQ5_K_M · ~15 tok/sdetails
Mac M2 24GB24 GBQ8_0 · ~8 tok/sdetails
Mac M3 24GB24 GBQ8_0 · ~8 tok/sdetails
Mac M4 Pro 24GB24 GBQ8_0 · ~23 tok/sdetails
Mac M4 32GB32 GBQ8_0 · ~10 tok/sdetails
Mac M1 Pro 32GB32 GBQ8_0 · ~17 tok/sdetails
Mac M3 Pro 36GB36 GBQ8_0 · ~13 tok/sdetails
Mac M4 Pro 48GB48 GBF16 · ~12 tok/sdetails
Mac M4 Pro 64GB64 GBF16 · ~12 tok/sdetails
Mac M1 Max 64GB64 GBF16 · ~18 tok/sdetails
Mac M4 Max 64GB64 GBF16 · ~24 tok/sdetails
Mac M2 Max 96GB96 GBF16 · ~18 tok/sdetails
Mac M3 Max 128GB128 GBF16 · ~18 tok/sdetails
Mac M4 Max 128GB128 GBF16 · ~24 tok/sdetails
Mac M2 Ultra 192GB192 GBF16 · ~36 tok/sdetails
Mac M3 Ultra 256GB256 GBF16 · ~37 tok/sdetails
Mac M3 Ultra 512GB512 GBF16 · ~37 tok/sdetails

Questions

How much VRAM do I need for KORMo Web 11B?

About 8.3 GB at 4-bit (Q4_K_M) with an 8K context, including KV cache and runtime overhead. Longer contexts need more; the model page has the full table by quant and context.

Other popular checks: Can I run gpt-oss-120b?Can I run gpt-oss-20b?Can I run Llama 70B?Can I run Qwen3?Can I run DeepSeek R1? · Best GPU by budget · Mac vs PC

Model data: Hugging Face Hub API and GGUF file sizes. GPU specs: vendor pages. Speeds are estimates, not benchmarks. Methodology · Report an error.