Best local LLMs for 48 GB of VRAM or unified memory

Measured speeds from builds where the model ran on more than 32 and up to 48 GB of GPU or unified memory. Each number links to its build and source.

8 GB · 12 GB · 16 GB · 24 GB · 32 GB · 48 GB · 64 GB · 96 GB · 128 GB or more

Fastest measured result per model

Excludes results the source marks pending and results where part of the model sat in system RAM.

All results in this tier

Hide speculative-decoding results ⚡ (MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)

What fits by memory math

Q4_K_M weights (4.8944 bits per weight, per the llama.cpp quantize table) that fit in 48 GB with ~5% headroom, before KV cache: Nemotron 3.5 Bolt 74B-A9B ≈45 GB, Llama 3.3 70B ≈43 GB, Flint 40B-A2.5B ≈24 GB, Ornith 1.5 35B-A3B ≈22 GB, Qwen3.6 35B-A3B ≈22 GB, Gemma 4 31B ≈19 GB, Nemotron 3.5 Lightning 30B-A3B ≈18 GB, Qwen3.6 27B ≈17 GB, Qwen3.8 27B ≈17 GB, Gemma 4 26B-A4B ≈15 GB, Devstral Small 2 24B ≈15 GB, LFM2.5 24B-A2B ≈15 GB, gpt-oss 20B ≈13 GB, Gemma 4 12B ≈7 GB, Qwen3.5 9B ≈5 GB, Llama 3.1 8B ≈5 GB.

FAQ

Which local LLMs have been measured on 48 GB of VRAM?

Llama 3 70B, Llama 3.3 70B, gpt-oss 20B, Qwen3.6 35B-A3B, Qwen3.8 27B, Qwen3.5 9B, Flint 40B-A2.5B, Qwen3.8 Flash-Next (19 results).

What fits in 48 GB of VRAM?

By memory math at Q4_K_M (4.8944 bits per weight, llama.cpp), weights only, before KV cache and context: Nemotron 3.5 Bolt 74B-A9B (≈45 GB), Llama 3.3 70B (≈43 GB), Flint 40B-A2.5B (≈24 GB), Ornith 1.5 35B-A3B (≈22 GB), Qwen3.6 35B-A3B (≈22 GB), Gemma 4 31B (≈19 GB), Nemotron 3.5 Lightning 30B-A3B (≈18 GB), Qwen3.6 27B (≈17 GB). Leave a few GB for context.

Are speculative-decoding results comparable?

Not 1:1. MTP, DFlash and similar methods draft tokens that the main model verifies, which can double tok/s on predictable text. This page lists them in a separate column; tick the box to hide them in the full table.