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

Can I run SenseNova Loop 9B on my PC?

New release: SenseNova Loop 9B was published on Hugging Face on Nov 17, 2026 by sensenova. Numbers update hourly as GGUF files appear. See everything new this week.

SenseNova Loop 9B (9.4B) needs about 6.4 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). The smallest Mac that runs it is the Mac M4 16GB.

6.4 GBneeded at 4-bit, 8K
53GPUs/Macs: fully in memory
0GPUs: with CPU offload
M4 16GBsmallest Mac

SenseNova Loop 9B 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 GBQ4_K_M · ~51 tok/sdetails
RTX 40608 GBQ4_K_M · ~48 tok/sdetails
RTX 50608 GBQ4_K_M · ~80 tok/sdetails
RTX 3060 Ti8 GBQ4_K_M · ~80 tok/sdetails
RTX 4060 Ti 8GB8 GBQ4_K_M · ~51 tok/sdetails
RTX 30708 GBQ4_K_M · ~80 tok/sdetails
RTX 3080 10GB10 GBQ6_K · ~98 tok/sdetails
Arc B58012 GBQ8_0 · ~48 tok/sdetails
RTX 3060 12GB12 GBQ8_0 · ~38 tok/sdetails
RX 7700 XT12 GBQ8_0 · ~45 tok/sdetails
RTX 507012 GBQ8_0 · ~70 tok/sdetails
RTX 407012 GBQ8_0 · ~53 tok/sdetails
RTX 4070 Super12 GBQ8_0 · ~53 tok/sdetails
RTX 4070 Ti12 GBQ8_0 · ~53 tok/sdetails
RTX 3080 12GB12 GBQ8_0 · ~96 tok/sdetails
Arc A770 16GB16 GBQ8_0 · ~59 tok/sdetails
RTX 5060 Ti 16GB16 GBQ8_0 · ~47 tok/sdetails
RTX 4060 Ti 16GB16 GBQ8_0 · ~30 tok/sdetails
RX 7800 XT16 GBQ8_0 · ~65 tok/sdetails
RX 7900 GRE16 GBQ8_0 · ~60 tok/sdetails
RX 907016 GBQ8_0 · ~67 tok/sdetails
RX 9070 XT16 GBQ8_0 · ~67 tok/sdetails
RTX 5070 Ti16 GBQ8_0 · ~94 tok/sdetails
RTX 4070 Ti Super16 GBQ8_0 · ~70 tok/sdetails
RTX 4080 Super16 GBQ8_0 · ~77 tok/sdetails
RTX 508016 GBQ8_0 · ~101 tok/sdetails
RTX 408016 GBQ8_0 · ~75 tok/sdetails
RX 7900 XT20 GBQ8_0 · ~84 tok/sdetails
RX 7900 XTX24 GBF16 · ~51 tok/sdetails
RTX 309024 GBF16 · ~50 tok/sdetails
RTX 409024 GBF16 · ~54 tok/sdetails
RTX 3090 Ti24 GBF16 · ~54 tok/sdetails
RTX 509032 GBF16 · ~95 tok/sdetails
DGX Spark128 GBF16 · ~15 tok/sdetails
Ryzen AI Max+ 395 128GB128 GBF16 · ~14 tok/sdetails
Mac M1 16GB16 GBQ6_K · ~9 tok/sdetails
Mac M4 16GB16 GBQ6_K · ~16 tok/sdetails
Mac M2 24GB24 GBQ8_0 · ~10 tok/sdetails
Mac M3 24GB24 GBQ8_0 · ~10 tok/sdetails
Mac M4 Pro 24GB24 GBQ8_0 · ~29 tok/sdetails
Mac M4 32GB32 GBF16 · ~6 tok/sdetails
Mac M1 Pro 32GB32 GBF16 · ~11 tok/sdetails
Mac M3 Pro 36GB36 GBF16 · ~8 tok/sdetails
Mac M4 Pro 48GB48 GBF16 · ~15 tok/sdetails
Mac M4 Pro 64GB64 GBF16 · ~15 tok/sdetails
Mac M1 Max 64GB64 GBF16 · ~21 tok/sdetails
Mac M4 Max 64GB64 GBF16 · ~29 tok/sdetails
Mac M2 Max 96GB96 GBF16 · ~21 tok/sdetails
Mac M3 Max 128GB128 GBF16 · ~21 tok/sdetails
Mac M4 Max 128GB128 GBF16 · ~29 tok/sdetails
Mac M2 Ultra 192GB192 GBF16 · ~42 tok/sdetails
Mac M3 Ultra 256GB256 GBF16 · ~44 tok/sdetails
Mac M3 Ultra 512GB512 GBF16 · ~44 tok/sdetails

Questions

How much VRAM do I need for SenseNova Loop 9B?

About 6.4 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.