llamaperf

NVIDIA RTX 3080 10GB reports

5 reports. These are individual setups, not a controlled benchmark. NVIDIA RTX 3080 10GB speeds and models →

Speeds are as each source reported them. GPU count, offloading and concurrent requests change them, and prompt-processing speed is input throughput, not time to first token. Check the full setup before comparing two reports.

Tone: mixedNVIDIA hardware
generation:
85.0 tokens/s
prompt processing (prefill):
2900.0 tokens/s
quant:
i1-IQ3_XXS (GGUF)
codingagentictool-use

User reports Qwen3.6 35B-A3B (Opus distill, abliterated, i1-IQ3_XXS) at about 85 t/s generation and about 2900 t/s prompt processing on an RTX 3080 10GB plus RTX 2070 Super 8GB, with 124k context. Setup is llama.cpp (CUDA) with opencode; the model fits fully in VRAM. Generation drops to about 68 t/s at 30k context. User finds the speed fine but the output quality poor and suspects the 3-bit quant. A Qwen3-Coder 30B-A3B abliterated at i1-IQ4_XS ran about 33 t/s at 64k, but at 128k the KV cache pushed experts to CPU and it fell to about 17 t/s. Qwen3.5 35B abliterated on Ollama was fast but the code quality was not great. User asks for a middle ground with at least 90k context for agentic coding in C++ and Python.

Nov 19, 2026
Tone: positiveNVIDIA hardware
generation:
145-185 tokens/s
prompt processing (prefill):
3957.0 tokens/s
quant:
UD-IQ4_XS (GGUF)
codingagentic

User reports Qwen3.8-Flash-Next on 2x RTX 3080 10GB with experts in system RAM, reaching 3,957 t/s prefill at a 200K cold prompt and decode of ~145-185 t/s with UD-IQ4_XS. Setup is the Speedy fork of Strata with UD-IQ4_XS, a 200K-token cold prompt, two pipeline windows and speculative decoding; the box is a Threadripper PRO 5975WX with 128 GB DDR4-3200. Decode varies with reply length and context, sitting at the top of the range for short replies and the bottom after a 200K prompt; a 200K cold prompt took 51 s. The 1x RTX 3080 table gives ~113-128 t/s decode and 1,792 t/s prefill at 200K for the same quant.

Nov 10, 2026

Qwen3.5 4B

NVIDIA RTX 3080 10GB · llama.cpp · 704,000 ctx

NVIDIA hardware
prompt processing (prefill):
662.0 tokens/s
quant:
Q4_K_M (GGUF)
long-context

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.

Oct 29, 2026

Qwen3.8 27B

NVIDIA RTX 3080 10GB · Unsloth · 44,000 ctx

NVIDIA hardware
generation:
20-25 tokens/s
quant:
IQ3_XXS (GGUF)
agenticcoding

User asks whether replacing a GTX 1070 with an RTX 3060 12GB is worthwhile for local LLMs and agentic coding. Current setup is an RTX 3080 10GB plus GTX 1070 8GB, Ryzen 5 5600X, 32GB RAM. User reports running Qwen3.8 27B IQ3_XXS at about 20-25 tokens/s with 44K context using Unsloth, and wants at least 128K context. The 3060 upgrade is a purchase question, not a measured run; no throughput figure is reported for the proposed card.

Oct 5, 2026

Bonsai 2 27B

NVIDIA RTX 3080 10GB · llama.cpp · 32,768 ctx

NVIDIA hardware
generation:
52.2 tokens/s
prompt processing (prefill):
1210.6 tokens/s
quant:
PTQ1_0 (GGUF)
kv:
q8_0
coding

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.

Sep 28, 2026