Code GGUF models

132 GGUF models in the Code family, quantized by 42 uploaders. Sizes run from 42M to 33.7B parameters. The longest trained context is 986K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
CO
Code 13B
Code · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
Coding
CO
Code 290k 13B
Code · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
Coding
CO
models--mergekit-community--mergekit-slerp-fecxcxs
Code · MaziyarPanahi
Params22.7B
Context16K
Q4_K_M13.6 GB
Coding
CO
code review decisions
Code · yannelli
Params2.7B
Context32K
Q4_K_M1.7 GB
CodingReasoningTool use
CO
Code 290k 13B
Code · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
Coding
CO
ajibawa-2023_code-33b
Code · TheBloke
Params32.5B
Context2K
Q4_K_M19.6 GB
Coding
CO
E1 Code 14B
Code · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingReasoningTool use
CO
Code 290k 6.7B Instruct
Code · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
CO
Code 290k 6.7B Instruct
Code · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
CO
code-stral-7B-B
Code · mradermacher
Params19.8B
Context32K
Q4_K_M11.9 GB
Coding
CO
d1 3b code review decisions ollama
Code · yannelli
Params2.7B
Context32K
Q4_K_M1.7 GB
CodingReasoningTool use
CO
Code 13B
Code · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
Coding
CO
code autocomplete gpt2 base i1
Code · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
Coding
CO
iq code evmind 14b i1
Code · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
CodingTool use
CO
code-stral-AB
Code · mradermacher
Params19.8B
Context32K
Q4_K_M11.9 GB
Coding
CO
R1 Code Interpreter 14B
Code · mradermacher
Params14.8B
Context986K
Q4_K_M9.0 GB
CodingReasoningTool use
CO
Code As World VL 9B
Code · prithivMLmods
Params8.95B
Context256K
Q4_K_M5.6 GB
CodingReasoningTool use
CO
Code As World VL 4B
Code · prithivMLmods
Params4.84B
Context256K
Q4_K_M3.1 GB
CodingReasoningTool use
CO
E1 Code 14B
Code · mradermacher
Params14.8B
Context128K
Q4_K_M9.0 GB
CodingReasoningTool use
CO
Code 290k 6.7B Instruct
Code · RichardErkhov
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
CO
Code 290k 13B
Code · mradermacher
Params13B
Context4K
Q4_K_M7.9 GB
Coding
CO
code embed v2
Code · divakantpandey
Params125M
Context1K
Smallest0.1 GB
CodingEmbedding
CO
Iq Code Evmind 0.5b Instruct v0.2411.0 193
Code · RichardErkhov
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
CO
Code Simple Rl 1.5b
Code · mradermacher
Params1.78B
Context128K
Q4_K_M1.1 GB
CodingTool use
CO
code 3b i1
Code · mradermacher
Params3.4B
Context32K
Q4_K_M2.1 GB
CodingTool use
CO
Code2World
Code · mradermacher
Params8.19B
Context256K
Q4_K_M5.0 GB
Tool useVision
CO
code autocomplete gpt2 base
Code · mradermacher
Params124M
Context1K
Q4_K_M0.1 GB
Coding
CO
Iq Code Evmind 14b Instruct v0.2411.2
Code · MaziyarPanahi
Params14.8B
Context32K
Smallest10.3 GB
CodingTool use
CO
Iq Code Evmind 7b Instruct v0.2411.0
Code · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
CO
iq code evmind 7b i1
Code · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use

About the Code GGUF models

Code is represented on ggufmodels.com by 132 GGUF models, quantized by 42 uploaders on Hugging Face. The most downloaded are Code 13B, Code 290k 13B and models--mergekit-community--mergekit-slerp-fecxcxs. Parameter counts run from 42M to 33.7B, and the longest trained context window is 986K tokens.

A Q4_K_M file of a Code model is between 0.1 to 20.2 GB, which is the quant most people start with. Most files come from mradermacher (42), microtensor-archive (11) and RichardErkhov (11). The quants you will meet most often are Q4_K_M (75), Q2_K (67), Q5_K_M (65) and Q3_K_M (65), where the number is how many models offer that quant.

Frequently asked questions

Which Code GGUF should I download?

The most downloaded Code GGUF here is Code 13B. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Code model need?

Q4_K_M files of Code models on this site range from 0.1 to 20.2 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Code GGUF files come from?

The most common quantizers here are mradermacher, microtensor-archive and RichardErkhov. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing