DeepSeek-Coder-V2-Lite Instruct

16B

DeepSeek

MoE architecture coding model. Active params ~2.4B, total ~16B. Exceptional code quality.

466.7K HF downloads192 likesbartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF· stats from 9/21/2026
Consumer GPUMac / Apple Silicon

164K

Max Context

3

Quant Variants

GGUF Q8_0

Best Quality

99.8%

Accuracy Retained

Quantization Variants

Per-quant VRAM, quality loss, and inference speed on RTX 4090

Measured = site benchmarks · Estimated = formula · Community = public reports

FormatLevelBPWVRAMPPL LossSpeedSourceActions
GGUFQ4_K_M4.8511.1 GB3.1%145 tok/sEstimated
CalcHF
GGUFQ8_08.517.5 GB0.2%118 tok/sEstimated
CalcHF
AWQINT449.8 GB4.1%192 tok/sEstimated
CalcHF

Running DeepSeek-Coder-V2-Lite Instruct locally

At Q4_K_M and 4K of context, DeepSeek-Coder-V2-Lite Instruct needs about 10.9 GB — 9.0 GB of weights, 0.84 GB of KV cache and a 1.0 GB activation buffer. The smallest card in this index that clears that comfortably is the RTX 5080 at 16 GB, and 46 of the 63 cards here do. These are calculated figures, not measurements: the estimate stops counting a card as comfortable at 88% of its VRAM, which is roughly the room a desktop session needs.

What longer context costs

Going from 4K to 32K adds about 5.91 GB, taking the total to 17.4 GB. Weights do not move with context — only the KV cache does, and it grows linearly, so this is the number to watch when planning for long documents. The model's native window is 160K; holding all of it at Q4_K_M would need about 47 GB.

Which build to download

This index tracks 2 formats for it — GGUF, AWQ — across 3 levels. Q8_0 carries the lowest published perplexity loss at 0.2%. The fastest level measured here is AWQ INT4 at 192 tok/s on an RTX 4090, batch 1. GGUF runs on llama.cpp and Ollama across NVIDIA, AMD and Apple silicon; AWQ and GPTQ target vLLM on CUDA and ROCm; EXL2 is ExLlamaV2 and CUDA only.

Common questions

How much VRAM does DeepSeek-Coder-V2-Lite Instruct need?
About 10.9 GB at Q4_K_M with 4K of context and batch 1, rising to roughly 17.4 GB at 32K. That figure is weights plus KV cache plus a 10% activation buffer, calculated from the model's architecture rather than measured on a card.
Will DeepSeek-Coder-V2-Lite Instruct run on a 16GB GPU?
Yes — at Q4_K_M and 4K context it needs about 10.9 GB, which leaves 5.1 GB spare on a RTX 5080. That is the smallest card in this index that clears it comfortably; 46 of 63 do.
Which quantization of DeepSeek-Coder-V2-Lite Instruct should I use?
Q8_0 has the lowest published quality loss (0.2%), and Q4_K_M is the level most people run. All 3 levels in the index are Q4_K_M, Q8_0, AWQ INT4.

Where this model fits

Sized at Q4_K_M with a 4K context window, smallest card first. Comfortable means the estimate uses at most 88% of the memory.

Ships in
GGUFAWQ
Compared here
GGUF vs AWQ

This page's figures change when the model or the runtime does.Last updated 2026-09-21 RSS → /feed.xml