More
Best rig by budgetRent before you buySubmit a buildNewsletterFree datasetAdvertise
Submit build

Builds / RTX 4090 24GB

EPYC 7642 + RTX 4090 + 252 GB RAM: Qwen3.8 27B Q4_K_M at 43.1 tok/s (llm-speed community run)

Last updated:

Source: llm-speed.com ↗📏 How measured: reported by the original source; RigBase re-checked the numbers at that source
GPU(s)
RTX 4090 24GB
Amazon · eBay (used) · Newegg
VRAM / unified memory (GB)
24
CPU
AMD EPYC 7642 (48 cores)
Amazon · eBay (used) · Newegg
Motherboard
not stated
RAM
252 GB (as reported)
Amazon · eBay (used) · Newegg
PSU
not stated
Other
not stated
Reported total cost
not stated
Power
not stated

Measured speed (generation tokens/sec)

ModelQuantEnginetok/sPrompt processing (tok/s)Details
Qwen3.8 27BQ4_K_Mllama.cpp (df18bee)43.06429 @ 154-token prompt
measured TTFT: 0.36 s @ 154-token prompt		context: chat-short (154-token prompt)📏 Signed community run r_11kn1epxewh, 14 Oct 2026; concurrent-decode 43.00, agent-trace 42.07
Qwen3.8 27BQ4_K_Mllama.cpp (df18bee)42.631,915 @ 3,224-token prompt
est. TTFT @8k ≈ 4.3 s (calculated from measured prefill)
measured TTFT: 1.7 s @ 3,224-token prompt		context: chat-long (3,224-token prompt)📏 Same run, chat-long workload

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.

Community-submitted signed run on llm-speed.com (signed on the submitter's machine, not measured by llm-speed). GPU, CPU and RAM as reported by the run; motherboard and PSU not stated.

Current GPU street price (estimate, not the builder's cost)Estimated GPU cost for this build today: ≈€3,955
New retail prices in Germany incl. VAT; used cards are often much cheaper. Prices change daily.
Source: https://llm-speed.com/r/r_11kn1epxewh

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/epyc-7642-rtx-4090-252gb-qwen38-27b-llmspeed.svg)](https://getrigbase.com/builds/epyc-7642-rtx-4090-252gb-qwen38-27b-llmspeed/)

HTML

<a href="https://getrigbase.com/builds/epyc-7642-rtx-4090-252gb-qwen38-27b-llmspeed/" rel="noopener"><img src="https://getrigbase.com/badge/epyc-7642-rtx-4090-252gb-qwen38-27b-llmspeed.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 4090 run Qwen3.8 27B?