StarCoder GGUF models

211 GGUF models in the StarCoder family, quantized by 65 uploaders. Sizes run from 7M to 42.1B parameters. The longest trained context is 40K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ST
Dolphincoder Starcoder2 15b
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M9.9 GB
CodingTool use
ST
StarCoder
StarCoder · mradermacher
Params15.5B
Context8K
Q4_K_M10.0 GB
Coding
ST
Starcoder
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
ST
Starcoder2 15b
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
Starcoder2 3b
StarCoder · mradermacher
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
ST
Starcoderplus
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
ST
starcoder2-7b
StarCoder · second-state
Params7.17B
Context16K
Q4_K_M4.4 GB
Coding
ST
starcoder2-15b
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M10.2 GB
Coding
ST
starcoder2-15b
StarCoder · QuantFactory
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2-15b
StarCoder · second-state
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2-3b
StarCoder · second-state
Params3.03B
Context16K
Q4_K_M1.8 GB
Coding
ST
Dolphincoder Starcoder2 15b
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M9.9 GB
CodingTool use
ST
dolphincoder starcoder2 15b
StarCoder · dagbs
Params16B
Context16K
Q4_K_M9.9 GB
CodingTool use
ST
starcoder2-15b-instruct-v0.1
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
Starcoderbase
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
ST
starcoder2 7b
StarCoder · QuantFactory
Params7.2B
Context16K
Q4_K_M4.5 GB
Coding
ST
Starcoder2 7b
StarCoder · QuantFactory
Params7.17B
Context16K
Q4_K_M4.5 GB
Coding
ST
Starcoder2 3b
StarCoder · QuantFactory
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
ST
Starcoder
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
ST
StarCoder
StarCoder · mradermacher
Params15.5B
Context8K
Q4_K_M10.0 GB
Coding
ST
Starcoderbase
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding
ST
Starcoder2 3b
StarCoder · mradermacher
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
ST
starcoderbase 7b
StarCoder · QuantFactory
Params7.5B
Context8K
Q4_K_M4.9 GB
Coding
ST
starcoder2 3b
StarCoder · QuantFactory
Params3.03B
Context16K
Q4_K_M1.9 GB
Coding
ST
starcoder2-15b-instruct-rpgle
StarCoder · mradermacher
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2-15b-instruct-v0.1
StarCoder · second-state
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2-15b-instruct-v0.1
StarCoder · bartowski
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2-15b-instruct-v0.1
StarCoder · lmstudio-community
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
starcoder2 15b
StarCoder · QuantFactory
Params16B
Context16K
Q4_K_M9.9 GB
Coding
ST
Starcoderplus
StarCoder · mradermacher
Params15.8B
Context8K
Q4_K_M10.1 GB
Coding

About the StarCoder GGUF models

StarCoder is represented on ggufmodels.com by 211 GGUF models, quantized by 65 uploaders on Hugging Face. The most downloaded are Dolphincoder Starcoder2 15b, StarCoder and Starcoder. Parameter counts run from 7M to 42.1B, and the longest trained context window is 40K tokens.

A Q4_K_M file of a StarCoder model is between 0.1 to 25.9 GB, which is the quant most people start with. Most files come from mradermacher (54), RichardErkhov (35) and tensorblock (13). The quants you will meet most often are Q4_K_M (163), Q5_K_M (143), Q2_K (142) and Q3_K_M (141), where the number is how many models offer that quant.

Frequently asked questions

Which StarCoder GGUF should I download?

The most downloaded StarCoder GGUF here is Dolphincoder Starcoder2 15b. 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 StarCoder model need?

Q4_K_M files of StarCoder models on this site range from 0.1 to 25.9 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 StarCoder GGUF files come from?

The most common quantizers here are mradermacher, RichardErkhov and tensorblock. 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