Tulu GGUF models

104 GGUF models in the Tulu family, quantized by 15 uploaders. Sizes run from 268M to 69B parameters. The longest trained context is 128K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
TU
Tulu 2 7B Helpful
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
Tulu2 7b_writing Prompts
Tulu · RichardErkhov
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
TU
tulu 2 70b i1
Tulu · mradermacher
Params69B
Context8K
Q4_K_M41.4 GB
GGUF
TU
allenai_tulu-2-dpo-7b
Tulu · TheBloke
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
Tulu 2 7b
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
allenai_tulu-2-dpo-70b
Tulu · TheBloke
Params69B
Context8K
Q4_K_M41.4 GB
GGUF
TU
allenai_tulu-2-dpo-13b
Tulu · TheBloke
Params13B
Context8K
Q4_K_M7.9 GB
GGUF
TU
tulu 2 70b
Tulu · mradermacher
Params69B
Context8K
Q4_K_M41.4 GB
GGUF
TU
allenai_tulu-2-7b
Tulu · TheBloke
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
DR Tulu SFT 8B
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
TU
uf tulu 2 7b dpo full
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
Tulu 2 7b
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
DR Tulu No RLER 8B
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
TU
Tulu 2 7B Helpful
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
Tulu 2 Dpo 7b
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
Tulu3 RAG
Tulu · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
TU
tulu-2-dpo-70b
Tulu · RichardErkhov
Params69B
Context8K
Q4_K_M41.4 GB
GGUF
TU
DR Tulu SFT 8B
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
TU
DR Tulu 8B
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
TU
Tulu 3.1 8B SuperNova
Tulu · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
TU
Tulu MathLingo 8B
Tulu · bartowski
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
TU
DR Tulu 8B Step 1900
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
TU
Tulu 2 Dpo 7b
Tulu · mradermacher
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
allenai_tulu-7b
Tulu · TheBloke
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
TU
DR-Tulu-8B
Tulu · Mungert
Params8.19B
Context40K
Q4_K_M5.4 GB
ReasoningTool use
TU
Tulu 3.69 8B i1
Tulu · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
TU
Allenai.Tulu 2 Dpo 7b
Tulu · DevQuasar-8
Params6.74B
Context8K
Q4_K_M4.1 GB
GGUF
TU
allenai_tulu-30b
Tulu · TheBloke
Params32.5B
Context2K
Q4_K_M19.6 GB
GGUF
TU
Tulu Tree Fiddy 8B i1
Tulu · mradermacher
Params8.03B
Context128K
Q4_K_M4.9 GB
Roleplay
TU
DR Tulu No RLER 8B
Tulu · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use

About the Tulu GGUF models

Tulu is represented on ggufmodels.com by 104 GGUF models, quantized by 15 uploaders on Hugging Face. The most downloaded are Tulu 2 7B Helpful, Tulu2 7b_writing Prompts and tulu 2 70b i1. Parameter counts run from 268M to 69B, and the longest trained context window is 128K tokens.

A Q4_K_M file of a Tulu model is between 0.4 to 41.4 GB, which is the quant most people start with. Most files come from mradermacher (71), TheBloke (9) and RichardErkhov (7). The quants you will meet most often are Q2_K (97), Q5_K_M (96), Q4_K_M (96) and Q3_K_M (95), where the number is how many models offer that quant.

Frequently asked questions

Which Tulu GGUF should I download?

The most downloaded Tulu GGUF here is Tulu 2 7B Helpful. 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 Tulu model need?

Q4_K_M files of Tulu models on this site range from 0.4 to 41.4 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 Tulu GGUF files come from?

The most common quantizers here are mradermacher, TheBloke 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