Local model performance on your hardware

generation:

43.0 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.

User reports Qwen3.6-35B-A3B at a little over 43 tokens/s on an RTX 5060 Laptop 8GB in a Lenovo Legion 5 with a Ryzen AI 7 350 and 32GB DDR5-5600. Setup is llama.cpp with the model offloaded across the 8GB VRAM and system RAM; around 30K context looks promising. User is also building PolyStrata to try for more performance, with no numbers yet.

generation:

29.3 tokens/s

quant:

PTQ1_0 (GGUF)

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.

User reports Ternary Bonsai 2 27B at 29.27 t/s on an RTX 5060 Laptop 8 GB under Windows, using a Prism llama.cpp build. Setup is llama.cpp with PTQ1_0 (5.53 GiB), temp 0, seed 42, a 2048 reasoning budget and a 3072 token cap on 50 MATH-500 questions. A −2 logit bias on "wait", "maybe" and "perhaps" (nine token ids) dropped accuracy from 44/50 to 43/50 and raised average tokens from 845.2 to 872.3; the biased run measured 29.28 t/s. The user calls it one deterministic data point, not proof.

generation:

40.0 tokens/s

prompt processing (prefill):

700-900 tokens/s

quant:

Q6_K (GGUF)

kv:

F16

Reported by the source; GPU count, offloading and concurrent requests can change these figures. Prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing.

User reports Gemma 4 12B at 40.0 t/s on an RTX 5060 Laptop GPU with 8 GB VRAM, using MTP speculative decoding with a Q6_K draft head and F16 KV cache at 4096 context. Setup is llama.cpp with mainline draft-mtp support (commit b9193 or later), an imatrix-guided per-tensor fit-to-VRAM quant at 6.18 GB, 48 layers, parallel 1. Prefill is 700 to 900 t/s. Without MTP the same setup reaches 27.4 t/s. With a Q8 KV cache it reaches 40.4 t/s. In real chat use the user sees 42 or more t/s on fresh context, dropping to 33 to 37 t/s with 16k of context filled.