More
Submit build

Builds / RTX 5090

RTX 5090: Qwen3.8 27B NVFP4 GGUF at 84.8 tok/s vs stock Q4_K_M at 81.2 on llama.cpp CUDA, prefill 5,081 vs 3,947 (LibertAI card)

Last updated:

Source: huggingface.co ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
GPU(s)
RTX 5090
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
32
CPU
not stated
Amazon · eBay (used) · Newegg
Motherboard
not stated
Amazon · eBay (used) · Newegg
RAM
not stated
Amazon · eBay (used) · Newegg
PSU
not stated
Other
CUDA 13.0, sm_120; llama.cpp build 849798132; llama-bench single stream, 3 repetitions; NVFP4 on the MLP linears only (ModelOpt PTQ, group 16), attention / Gated-DeltaNet / embeddings in Q4_K_M or Q8_0
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Qwen3.8 27BNVFP4-Q4_K_M GGUF (LibertAI; 14.72 GiB)llama.cpp 849798132 (CUDA 13.0)84.85,081 @ 512-token prompt
est. TTFT @8k ≈ 1.6 s (calculated from measured prefill)
context: llama-bench tg64📏 llama-bench, 3 reps; batched (llama-batched-bench 512 in / 128 out) total 398 tok/s at 1 stream, 1,520 at 8
Qwen3.8 27BNVFP4-Q8_0 GGUF (LibertAI; 18.65 GiB)llama.cpp 849798132 (CUDA 13.0)71.85,169 @ 512-token prompt
est. TTFT @8k ≈ 1.6 s (calculated from measured prefill)
context: llama-bench tg64📏 llama-bench, 3 reps; larger Q8_0 attention tensors cost decode speed
Qwen3.8 27BQ4_K_M (stock, made from the same BF16; 15.40 GiB)llama.cpp 849798132 (CUDA 13.0)81.23,947 @ 512-token prompt
est. TTFT @8k ≈ 2.1 s (calculated from measured prefill)
context: llama-bench tg64📏 llama-bench, 3 reps; batched total 376 tok/s at 1 stream, 1,188 at 8

Prompt processing = prefill speed (how fast the prompt is read) as reported by the source, with the prompt length it was measured at; blank = the source does not report it. est. TTFT @8k is calculated from the measured prefill speed (8,192 ÷ prefill tok/s), shown only when prefill was measured on a prompt of 512+ tokens. It is not a measurement and ignores load time and caching. measured TTFT is the source's own time-to-first-token. Why prefill matters for coding assistants.

Quant publisher's own same-build comparison on one RTX 5090 (model card, Aug 2026). Native NVFP4 math needs a Blackwell GPU and llama.cpp built with CUDA 12.8+; on older cards the files load but the speed-up does not apply. The decode gain is small (+4%); the bigger wins are prefill (+29%) and batched serving (+28% at 8 parallel requests). tg64 is a short test. Quality: calibrated on English news text only, not tested on code or other languages.

Current GPU street price (estimate, not the builder's cost)Estimated GPU cost for this build today: ≈€7,140
New retail prices in Germany incl. VAT; used cards are often much cheaper. Prices change daily.
Source: https://huggingface.co/LibertAIDAI/Qwen3.8-27B-NVFP4-GGUF

Blank fields = not stated in the source. We never estimate build data; GPU street prices above are separately sourced and dated.

Embed this result

Copy into a README or blog. Links back to this build. See badge docs (CC BY 4.0 attribution). The SVG does not invent speeds — numbers stay on the build page.

Markdown

[![Measured on RigBase](https://getrigbase.com/badge/rtx-5090-qwen38-27b-nvfp4-gguf-vs-stock-q4km-llamacpp-libertai.svg)](https://getrigbase.com/builds/rtx-5090-qwen38-27b-nvfp4-gguf-vs-stock-q4km-llamacpp-libertai/)

HTML

<a href="https://getrigbase.com/builds/rtx-5090-qwen38-27b-nvfp4-gguf-vs-stock-q4km-llamacpp-libertai/" rel="noopener"><img src="https://getrigbase.com/badge/rtx-5090-qwen38-27b-nvfp4-gguf-vs-stock-q4km-llamacpp-libertai.svg" alt="Measured on RigBase" height="20"/></a>

Preview: Measured on RigBase · How to use

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

Quick answers: Can RTX 5090 run Qwen3.8 27B?