bartowski
DeepSeek-Coder-V2-Lite-Instruct
- Parameters
- 15.7B
- Max context length
- 163,840
- Architecture
- deepseek2
- License
- Unverified
- License
- deepseek-license
About DeepSeek-Coder-V2-Lite-Instruct
DeepSeek-Coder-V2-Lite-Instruct is a model published in GGUF format. GGUF files are published by bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF. It has about 15.7B parameters, the deepseek2 architecture, a maximum context length of 163,840 tokens (values written in the GGUF).
There are 21 quantizations, with file sizes from 5.97 GB (IQ2_XS) to 62.8 GB (F32) (actual sizes on Hugging Face).
Running Q4_K_M (10.4 GB) with an 8,192-token context needs an estimated 13.4 GB of memory, and an estimated 20.2 GB at 32,768 tokens. For 8,192 tokens, a GPU with 16 GB or more of VRAM (such as GeForce RTX 5080, GeForce RTX 5070 Ti), or a Mac with 16 GB or more of unified memory, is a rough guide (macOS caps how much memory the GPU can use, so leave some headroom). The smallest, IQ2_XS (5.97 GB), needs an estimated 8.98 GB at 8,192 tokens.
According to bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF, the license is deepseek-license. Check the original license for the terms of use.
File size and estimated memory per quantization
- Up to 8 GB
- Up to 16 GB
- Up to 24 GB
- Up to 48 GB
- Up to 128 GB
- More
File sizes are the actual values on Hugging Face. Memory is estimated for each context length (KV cache f16). The formula is in How memory is calculated.
All memory figures are Estimated (KV cache f16). It should run on a setup with at least this much VRAM (or Mac unified memory). Click a value to see the devices and models that fit that amount (Find by GPU / Mac).
About the "quality guide" (how far a quantization drifts from the original)
For each quantization type, how far the output drifts from the original model, grouped into six levels from values llama.cpp measured on Llama-3-8B.
The value is mean KLD (the difference between the original and quantized model in next-token probabilities); smaller means closer to the original. Quantizations made with an imatrix (importance data) come out slightly smaller. Levels use the value without an imatrix (or with one, for types that only have that).
These values were not measured on this model. Larger models and MoE models tend to drift less with the same type. Distributor-specific mixed types (such as UD-Q4_K_XL) cannot be matched by type name alone, so they show "-".
| Quantization | Quality guide | KLD (no imatrix) | KLD (imatrix) | Size (Llama-3-8B) |
|---|---|---|---|---|
| Q8_0 | Nearly identical | 0.0014 | - | 7.96 GiB |
| Q6_K | Very small | 0.0055 | - | 6.14 GiB |
| Q5_K_M | Very small | 0.0108 | - | 5.33 GiB |
| Q5_K_S | Small | 0.0166 | - | 5.21 GiB |
| Q5_1 | Small | 0.0180 | - | 5.65 GiB |
| Q5_0 | Small | 0.0222 | - | 5.21 GiB |
| Q4_K_M | Small | 0.0313 | 0.0282 | 4.58 GiB |
| Q4_K_S | Medium | 0.0431 | 0.0320 | 4.37 GiB |
| IQ4_NL | Small | - | 0.0357 | 4.35 GiB |
| IQ4_XS | Small | - | 0.0363 | 4.14 GiB |
| Q4_1 | Medium | 0.0717 | - | 4.78 GiB |
| Q4_0 | Medium | 0.0719 | - | 4.34 GiB |
| Q3_K_L | Medium | 0.0872 | 0.0731 | 4.03 GiB |
| Q3_K_M | Medium | 0.1019 | 0.0844 | 3.74 GiB |
| IQ3_M | Medium | - | 0.1025 | 3.53 GiB |
| IQ3_S | Medium | - | 0.1113 | 3.42 GiB |
| IQ3_XS | Large | - | 0.1387 | 3.28 GiB |
| IQ3_XXS | Large | - | 0.1836 | 3.05 GiB |
| Q3_K_S | Large | 0.2282 | 0.1998 | 3.41 GiB |
| IQ2_M | Large | - | 0.3260 | 2.74 GiB |
| Q2_K | Very large | 0.4451 | 0.3322 | 2.96 GiB |
| Q2_K_S | Very large | - | 0.4034 | 2.96 GiB |
| IQ2_S | Very large | - | 0.4392 | 2.56 GiB |
| IQ2_XS | Very large | - | 0.5463 | 2.43 GiB |
| IQ2_XXS | Very large | - | 0.8120 | 2.24 GiB |
| IQ1_M | Very large | - | 1.3931 | 2.01 GiB |
| IQ1_S | Very large | - | 2.2546 | 1.88 GiB |
Source: llama.cpp (MIT), measured on Llama-3-8B against FP16, Wikitext-2, revision f364eb6f. Original table · Reading and choosing quantizations
GGUF source
bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF
Published by the original developer About this label
Last checked: Nov 11, 2026
- Architecture
- deepseek2
- Supported before llama.cpp b4409
- Parameters
- 15.7B
- Max context length
- 163,840
- License
- deepseek-license Unverified
Ollama ollama run hf.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
llama.cpp llama-server -hf bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
License and commercial use
deepseek-license Unverified
This site has not verified this license text yet. Check the original before commercial use.
The original model's license has not been fetched yet, so this is based on the GGUF repository's label.
The summary states facts this site read from the original text and is not legal advice. Always check the original license and its latest terms before use. All licenses
How to run
Example commands using Q4_K_M. To use another quantization, replace the name with one from the table above. How to run local LLMs
Ollama
Run it by pointing directly at the GGUF on Hugging Face.
ollama run hf.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
llama.cpp
Pass the repository and quantization name to llama-server (or llama-cli) with -hf.
llama-server -hf bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
LM Studio
Paste bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF into the search box, download it, and choose the quantization from the file list.
Other models from bartowski
-
8B
bartowski
L3-8B-Stheno-v3.2
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
-
7.2B
bartowski
Mistral-7B-Instruct-v0.3
- Q4_K_M size
- 4.37 GB
- Memory at 8K
- 6.05 GB
Measured Estimated VRAM 6 GB+
-
107.8B
bartowski
meta-llama_Llama-4-Scout-17B-16E-Instruct-old
- Q4_K_M size
- 67.5 GB
- Memory at 8K
- 70.1 GB
Measured Estimated VRAM 96 GB+
-
79.7B
bartowski
huihui-ai_Qwen3-Coder-Next-abliterated
- Q4_K_M size
- 48.6 GB
- Memory at 8K
- 49.7 GB
Measured Estimated VRAM 48 GB+
-
8B
bartowski
Meta-Llama-3-8B-Instruct
- Q4_K_M size
- 4.92 GB
- Memory at 8K
- 6.79 GB
Measured Estimated VRAM 8 GB+
Models of a similar size (other developers)
-
11.9B
google
gemma-4-12B-it
- Q4_K_M size
- 7.12 GB
- Memory at 8K
- 8.83 GB
Measured Estimated VRAM 12 GB+
-
11.9B
google
gemma-4-12B-it-qat-q4_0
- Q4_0 size
- 6.98 GB
- Memory at 8K
- 8.69 GB
Measured Estimated VRAM 12 GB+
-
11.9B
HauhauCS
Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced
- Q4_K_M size
- 7.38 GB
- Memory at 8K
- 9.09 GB
Measured Estimated VRAM 12 GB+
-
20.9B
openai
gpt-oss-20b
- Q4_K_M size
- 11.6 GB
- Memory at 8K
- 12.8 GB
Measured Estimated VRAM 12 GB+
-
12.1B
JetBrains
Mellum2.1-12B-A2.5B-Thinking
- Q4_K_M size
- 8.07 GB
- Memory at 8K
- 8.99 GB
Measured Estimated VRAM 12 GB+
-
14.8B
Qwen
Qwen3-14B
- Q4_K_M size
- 9.00 GB
- Memory at 8K
- 11.2 GB
Measured Estimated VRAM 12 GB+
Frequently asked questions
- How much memory do I need to run DeepSeek-Coder-V2-Lite-Instruct (Q4_K_M)?
- The file size is 10.4 GB (measured). With a 8,192-token context, the estimated memory including the KV cache is 13.4 GB. The formula is published at https://localllm.az-arte.com/en/guide/memory-calculation.
- Can DeepSeek-Coder-V2-Lite-Instruct be used commercially?
- The license is deepseek-license (Commercial use not verified). Check the original license text before deciding.
- Does DeepSeek-Coder-V2-Lite-Instruct run in 8 GB, 12 GB, 16 GB or 24 GB of VRAM?
- 8 GB: no quantization fits; 12 GB: up to Q4_K_S (est. 12.5 GB); 16 GB: up to Q6_K (est. 17.1 GB); 24 GB: up to Q8_0 (est. 20.1 GB) (estimated at 8,192 tokens with an f16 KV cache, files from the most-downloaded source).
- What is the command to run DeepSeek-Coder-V2-Lite-Instruct with Ollama?
- Run "ollama run hf.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M" to use the GGUF on Hugging Face directly. To use another quantization, replace the name at the end.