Private AI ComputerBY WEB ASSET HOUSE
Models / SmolLM2-1.7B-Instruct

Model field guide

SmolLM2-1.7B-Instruct

42 of 44 hardware configurations have a supported memory fit at one or more recorded quantizations. Runtime compatibility still needs verification.

Total parameters1.71B
Active parameters1.71B
Recorded context limit8,192
Architecturedense
Customize the estimate ↗Official model record

Verified 2026-10-22 · license metadata: apache-2.0 · commercial use: yes (review the terms).

Actual files, not a size shortcut.

Recorded complete GGUF file sets
QuantizationTotal file sizeSource
Q4_K_M0.983 GiB1,055,609,536 bytes; 1 file(s)Sum of exact file byte sizes in the repository listing at the recorded commit; every declared shard is present. Auxiliary vision projector and speculative-decoding files are excluded. Labels follow publisher filenames; mixed-precision expert tensors may remain in a differently labeled file, so the estimator uses measured bytes rather than assumed bits per weight.Pinned file recordVerified 2026-10-22

The hardware picture.

Q4_K_M: hardware comparison
SmolLM2-1.7B-Instruct · Q4_K_M · default context up to 4,096 tokens · estimated fit and speed
HardwareUsable memoryRequired memoryFit estimateEstimated generation
Mac mini M6 (12-core GPU) 16GB12.0 GiB2.73 GiBfits58.0–116.0 estimated tokens/s
Mac mini M6 (12-core GPU) 24GB18.0 GiB2.73 GiBfits64.4–128.8 estimated tokens/s
Mac mini M6 (12-core GPU) 32GB24.0 GiB2.73 GiBfits64.4–128.8 estimated tokens/s
Mac mini M5 Pro (15-core CPU / 16-core GPU) 24GB18.0 GiB2.73 GiBfits116.3–232.7 estimated tokens/s
Mac mini M5 Pro (15-core CPU / 16-core GPU) 48GB36.0 GiB2.73 GiBfits116.3–232.7 estimated tokens/s
Mac mini M5 Pro (15-core CPU / 16-core GPU) 64GB48.0 GiB2.73 GiBfits116.3–232.7 estimated tokens/s
Mac Studio M5 Max (32-core GPU) 36GB27.0 GiB2.73 GiBfits174.3–348.6 estimated tokens/s
Mac Studio M5 Max (40-core GPU) 64GB48.0 GiB2.73 GiBfits232.7–465.3 estimated tokens/s
Mac Studio M5 Max (40-core GPU) 128GB96.0 GiB2.73 GiBfits232.7–465.3 estimated tokens/s
Mac Studio M5 Ultra (30-core CPU / 64-core GPU) 96GB72.0 GiB2.73 GiBfits454.7–909.4 estimated tokens/s
Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 256GB192.0 GiB2.73 GiBfits454.7–909.4 estimated tokens/s
Mac Studio M5 Ultra (36-core CPU / 80-core GPU) 512GB384.0 GiB2.73 GiBfits454.7–909.4 estimated tokens/s
MacBook Pro 14-inch M5 (10-core GPU) 24GB18.0 GiB2.73 GiBfits58.0–116.0 estimated tokens/s
MacBook Pro 14-inch M5 Pro (20-core GPU) 48GB36.0 GiB2.73 GiBfits116.3–232.7 estimated tokens/s
MacBook Pro 16-inch M5 Max (40-core GPU) 128GB96.0 GiB2.73 GiBfits232.7–465.3 estimated tokens/s
Mac mini (2024) M4 (10-core GPU) 16GB12.0 GiB2.73 GiBfits45.5–90.9 estimated tokens/s
Mac mini (2024) M4 (10-core GPU) 24GB18.0 GiB2.73 GiBfits45.5–90.9 estimated tokens/s
Mac mini (2024) M4 (10-core GPU) 32GB24.0 GiB2.73 GiBfits45.5–90.9 estimated tokens/s
Mac mini (2024) M4 Pro (16-core GPU) 24GB18.0 GiB2.73 GiBfits103.4–206.9 estimated tokens/s
Mac mini (2024) M4 Pro (16-core GPU) 48GB36.0 GiB2.73 GiBfits103.4–206.9 estimated tokens/s
Mac mini (2024) M4 Pro (16-core GPU) 64GB48.0 GiB2.73 GiBfits103.4–206.9 estimated tokens/s
Mac Studio (2025) M4 Max (32-core GPU) 36GB27.0 GiB2.73 GiBfits155.4–310.7 estimated tokens/s
Mac Studio (2025) M4 Max (40-core GPU) 64GB48.0 GiB2.73 GiBfits206.9–413.8 estimated tokens/s
Mac Studio (2025) M4 Max (40-core GPU) 128GB96.0 GiB2.73 GiBfits206.9–413.8 estimated tokens/s
Mac Studio (2025) M3 Ultra (28-core CPU / 60-core GPU) 96GB72.0 GiB2.73 GiBfits310.3–620.7 estimated tokens/s
Mac Studio (2025) M3 Ultra (32-core CPU / 80-core GPU) 256GB192.0 GiB2.73 GiBfits310.3–620.7 estimated tokens/s
NVIDIA GeForce RTX 3060 12GB10.8 GiB2.73 GiBfits136.4–272.8 estimated tokens/s
NVIDIA GeForce RTX 3090 24GB21.6 GiB2.73 GiBfits354.7–709.4 estimated tokens/s
NVIDIA GeForce RTX 4060 Ti 16GB14.4 GiB2.73 GiBfits109.1–218.3 estimated tokens/s
NVIDIA GeForce RTX 4070 12GB GDDR6X10.8 GiB2.73 GiBfits191.0–382.0 estimated tokens/s
NVIDIA GeForce RTX 4080 16GB14.4 GiB2.73 GiBfits271.6–543.2 estimated tokens/s
NVIDIA GeForce RTX 4090 24GB21.6 GiB2.73 GiBfits382.0–763.9 estimated tokens/s
NVIDIA GeForce RTX 5060 Ti 16GB14.4 GiB2.73 GiBfits169.8–339.5 estimated tokens/s
NVIDIA GeForce RTX 5070 12GB10.8 GiB2.73 GiBfits254.6–509.3 estimated tokens/s
NVIDIA GeForce RTX 5070 Ti 16GB14.4 GiB2.73 GiBfits339.5–679.0 estimated tokens/s
NVIDIA GeForce RTX 5080 16GB14.4 GiB2.73 GiBfits363.8–727.5 estimated tokens/s
NVIDIA GeForce RTX 5090 32GB28.8 GiB2.73 GiBfits679.0–1358.1 estimated tokens/s
NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB86.4 GiB2.73 GiBfits679.0–1358.1 estimated tokens/s
NVIDIA RTX 6000 Ada Generation 48GB43.2 GiB2.73 GiBfits363.8–727.5 estimated tokens/s
Intel Arc B580 12GB10.8 GiB2.73 GiBfits172.8–345.6 estimated tokens/s
AMD Ryzen AI Halo, Ryzen AI Max+ 395, 128GB89.6 GiB2.73 GiBfits97.0–194.0 estimated tokens/s
NVIDIA DGX Spark 128GB / 4TB96.0 GiB2.73 GiBfits103.4–206.9 estimated tokens/s
2 × GeForce RTX 3090 24GB (conditional 48GB aggregate)40.8 GiB2.73 GiBNeeds verificationEstimated speed unavailable
2 × GeForce RTX 5090 32GB (conditional 64GB aggregate)54.4 GiB2.73 GiBNeeds verificationEstimated speed unavailable
A “fits” result checks estimated memory only. “Needs verification” preserves missing cache, vision, or placement information. All speed figures are estimated from the published bandwidth formula.
Field-level sources and verification dates