Stablelm GGUF models

117 GGUF models in the Stablelm family, quantized by 46 uploaders. Sizes run from 1.64B to 12.1B parameters. The longest trained context is 4K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
ST
stablelm 2 zephyr 1 6b
Stablelm · stabilityai
Params1.64B
Context4K
Smallest1.0 GB
GGUF
ST
stablelm tuned alpha 7b i1
Stablelm · mradermacher
Params7.87B
Context4K
Q4_K_M5.1 GB
GGUF
ST
stablelm zephyr 3b
Stablelm · TheBloke
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
ST
stablelm-zephyr-3b
Stablelm · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
ST
stablelm tuned alpha 7b
Stablelm · mradermacher
Params7.87B
Context4K
Q4_K_M5.1 GB
GGUF
ST
Stablelm Base Alpha 7b
Stablelm · mradermacher
Params7.87B
Context4K
Q4_K_M5.1 GB
GGUF
ST
stablelm-2-zephyr-1_6b
Stablelm · second-state
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ST
Stablelm Tuned Alpha 3b
Stablelm · mradermacher
Params3.64B
Context4K
Q4_K_M2.3 GB
GGUF
ST
StableLM 2 1.6B Chat
Stablelm · mradermacher
Params1.64B
Context4K
Q4_K_M1.0 GB
Tool use
ST
stablelm-2-12b
Stablelm · mradermacher
Params12.1B
Context4K
Q4_K_M7.4 GB
Coding
ST
stablelm-2-12b
Stablelm · mradermacher
Params12.1B
Context4K
Q4_K_M7.4 GB
Coding
ST
stablelm-zephyr-3b
Stablelm · duyntnet
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
ST
stablelm-2-12b-chat
Stablelm · stabilityai
Params12.1B
Context4K
Q4_K_M7.4 GB
Tool use
ST
stablelm-2-1_6b
Stablelm · afrideva
Params1.64B
Context4K
Q4_K_M1.0 GB
Coding
ST
Stablelm 3b Abliterated
Stablelm · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
Coding
ST
Stablelm 3b 4e1t
Stablelm · RichardErkhov
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
ST
Stablelm Tuned Alpha 7b
Stablelm · mradermacher
Params7.87B
Context4K
Q4_K_M5.1 GB
GGUF
ST
stablelm 2 1.6b uncensored
Stablelm · arzaan789
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ST
stablelm-2-1_6b
Stablelm · mradermacher
Params1.64B
Context4K
Q4_K_M1.0 GB
Coding
ST
stablelm-2-zephyr-1_6b
Stablelm · afrideva
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ST
stablelm 2 zephyr 1.6b uncensored
Stablelm · arzaan789
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ST
Stablelm Tuned Alpha 3b
Stablelm · mradermacher
Params3.64B
Context4K
Q4_K_M2.3 GB
GGUF
ST
Stablelm Roleplay V1 BetaTest
Stablelm · mradermacher
Params2.8B
Context4K
Q4_K_M1.7 GB
Roleplay
ST
stablelm-3b-4e1t
Stablelm · afrideva
Params2.8B
Context4K
Q4_K_M1.7 GB
Coding
ST
Ektome StableLM 2 1.6B Chat PristinelyUncensored
Stablelm · Zynerji
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ST
stablelm zephyr 3b
Stablelm · QuantFactory
Params2.8B
Context4K
Q4_K_M1.7 GB
GGUF
ST
stablelm-2-12b-chat
Stablelm · second-state
Params12.1B
Context4K
Q4_K_M7.4 GB
GGUF
ST
Stablelm 2 1_6b
Stablelm · RichardErkhov
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF
ST
Stablelm 2 12b
Stablelm · RichardErkhov
Params12.1B
Context4K
Q4_K_M7.4 GB
GGUF
ST
Stablelm 2 Zephyr 1_6b
Stablelm · mradermacher
Params1.64B
Context4K
Q4_K_M1.0 GB
GGUF

About the Stablelm GGUF models

Stablelm is represented on ggufmodels.com by 117 GGUF models, quantized by 46 uploaders on Hugging Face. The most downloaded are stablelm 2 zephyr 1 6b, stablelm tuned alpha 7b i1 and stablelm zephyr 3b. Parameter counts run from 1.64B to 12.1B, and the longest trained context window is 4K tokens.

A Q4_K_M file of a Stablelm model is between 1.0 to 7.4 GB, which is the quant most people start with. Most files come from mradermacher (26), RichardErkhov (13) and tensorblock (5). The quants you will meet most often are Q4_K_M (71), Q5_K_M (70), Q6_K (62) and Q3_K_M (62), where the number is how many models offer that quant.

Frequently asked questions

Which Stablelm GGUF should I download?

The most downloaded Stablelm GGUF here is stablelm 2 zephyr 1 6b. 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 Stablelm model need?

Q4_K_M files of Stablelm models on this site range from 1.0 to 7.4 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 Stablelm 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