Local model performance on your hardware

prompt processing (prefill):

662.0 tokens/s

quant:

Q4_K_M (GGUF)

User tests Qwen3.5-4B Q4_K_M on an RTX 3080 10GB with llama.cpp built from upstream PR 29827, flash attention on and ubatch 64, on a RULER-style multikey needle task. Prefill at a 709,596-token prompt (704K, YaRN x2.75) was about 662 tok/s, 18.4 minutes per run, peaking at 9,784 MiB VRAM. Stating the question before the document as well as after fixed all five configs that failed with question-last, at 256K and at 512K/704K with YaRN. One run per config, so the user calls it a strong signal on a small sample rather than a rate. In 10 paired trials at 256K with question last, q8_0 KV cache passed 7/10 at ~7,730 MiB peak and q4_0 passed 6/10 at ~5,680 MiB; 9 of 10 pairs gave identical answers and McNemar exact p = 1.0. The user notes 114-170 MiB showed as shared memory, f16 cache does not fit at 256K on this card, and the model rambles after answering.

generation:

52.2 tokens/s

prompt processing (prefill):

1210.6 tokens/s

quant:

PTQ1_0 (GGUF)

kv:

q8_0

User reports Bonsai 2 27B PTQ1_0 at 52.18 t/s generation and 1210.6 t/s prefill on an RTX 3080 10GB. Setup is llama.cpp (fork build prism-b10735-842b188, CUDA 12.8) with PTQ1_0 quant and q8_0 KV cache at 32K context, single card, batch 1, depth 0, -ngl 99 -fa on. User also benchmarks PQ2_0 at 61.38 t/s and Qwen3.8-27B-UD-IQ2_XXS at 44.46 t/s on the same card, and reports a context ladder up to 160K q4_0 at 9627 MiB peak VRAM. A LiveCodeBench v6 comparison gives PTQ1_0 32/50 pass@1 versus 16/50 for IQ2_XXS and 28/50 for PQ2_0.