llamaperf

DeepSeek-Coder-V2-Lite

1 report

DeepSeek-Coder-V2-Lite 16B · 2.4B active at 4-bit generates a median of 125.8 tokens per second on the M5 Pro 24GB, the hardware it is most run on, from one plain run (community reports, as of 22 Nov 2026).

As of 22 Nov 2026, DeepSeek-Coder-V2-Lite 16B · 2.4B active at 4-bit on each device, fastest first, with the median generation speed of plain runs (one device, one request, no speculative decoding, the whole model in its memory):

  • M5 Pro 24GBPP 363.9 t/s, one run
    125.8 t/s · one run

Bars are medians on one scale, 0 to 125.8 tokens/s. Press ▶ to watch text arrive at a row's speed.

DeepSeek-Coder-V2-Lite VRAM requirements by size and quant →

How does DeepSeek-Coder-V2-Lite run on your hardware?

Pick your GPU or Mac, then read the speeds people reported for DeepSeek-Coder-V2-Lite on it, or estimate memory fit and speed.

Free to use. No account needed. Memory estimates and community measurements are labelled separately.

Run DeepSeek-Coder-V2-Lite yourself? Add your numbers.

Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.

Reported performance for DeepSeek-Coder-V2-Lite

Filter this model’s reports by setup →
One report for this model so far, so treat the figures as early. Add yours.

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: positiveApple hardware
generation:
125.8 tokens/s
prompt processing (prefill):
363.9 tokens/s
quant:
4bit (MLX)
codingagentic

User benchmarks DeepSeek-Coder-V2-Lite-Instruct at 125.8 tok/s generation and 363.9 tok/s prompt processing on an Apple M5 Pro with 24GB unified memory. Setup is MLX with a 4bit quant (8.2GB) on a single machine, running a fixed coding task capped at 1500 output tokens. The model produced correct working code; the user notes that 24GB has a hard ceiling around 20GB models and that background downloads measurably affect tok/s.

Oct 3, 2026

Get a weekly email of new DeepSeek-Coder-V2-Lite reports on any GPU.

Email me new reports

Reported configurations

Individual observations from this page, not expected speeds or a ranking. Select a model to open its report, with the source and offloading conditions. Reported context may be a limit rather than actual input length.

Model / hardwareQuant / engineReported contextGeneration
DeepSeek-Coder-V2-Lite 16B (2.4B active)
M5 Pro 24GB
4bit
MLX
Not reported125.8 tokens/s

Frequently asked

What hardware do people run DeepSeek-Coder-V2-Lite on?

The hardware DeepSeek-Coder-V2-Lite 16B · 2.4B active at 4-bit is most run on: M5 Pro 24GB (125.8 t/s median, one run). Medians of plain runs, as of 22 Nov 2026.

Which inference engines do people use for DeepSeek-Coder-V2-Lite?

Reports of DeepSeek-Coder-V2-Lite name MLX (1 report), as of 22 Nov 2026.