GGUF models by leafspark

36 GGUF models quantized by leafspark on Hugging Face. Sizes run from 121M to 218B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.2 11B Vision Instruct
Llama · leafspark
Params9.78B
Context128K
Q4_K_M6.0 GB
Vision
LL
Llama-3-8B-Instruct-Gradient-4194k
Llama · leafspark
Params8B
Context1K
Q4_K_M4.9 GB
GGUF
LL
Reflection Llama 3.1 70B
Llama · leafspark
Params70.6B
Context128K
Smallest15.3 GB
Tool use
QW
Qwen2-VL-2B-Instruct
Qwen · leafspark
Params1.54B
Context32K
Smallest3.1 GB
Vision
LL
Meta Llama 3.1 405B Instruct
Llama · leafspark
Params210B
Context—
Smallest71.8 GB
GGUF
WI
wikichat v2
Wikichat · leafspark
Params215M
Context2K
Smallest0.3 GB
GGUF
LA
ai21labs_AI21 Jamba 1.5 Mini
Labs · leafspark
Params51.6B
Context256K
Smallest22.3 GB
Tool use
LL
Hermes-2-Pro-Llama-3-8B
Llama · leafspark
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
PI
Pixtral 12B 2409 hf text only
Pixtral · leafspark
Params12.2B
Context1000K
Smallest9.2 GB
Tool useVision
LL
Meta Llama 3.1 8B Instruct
Llama · leafspark
Params8.03B
Context128K
Smallest3.2 GB
GGUF
LL
Llama 3 Orca 1.0 8B
Llama · leafspark
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
WA
wavecoder ds 6.7b
Wavecoder · leafspark
Params6.74B
Context16K
Q4_K_M4.1 GB
Coding
LL
Magnum 72b v1 Llama
Llama · leafspark
Params72.7B
Context32K
Q4_K_M50.7 GB
GGUF
WI
wikichat
Wikichat · leafspark
Params121M
Context2K
Smallest0.2 GB
GGUF
LL
Meta Llama 3.1 8B Instruct Hf
Llama · leafspark
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
YI
Yi-1.5-9B-Chat-16K
Yi · leafspark
Params8.83B
Context16K
Q4_K_M5.3 GB
GGUF
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Smallest19.6 GB
GGUF
CE
L3.1 70B Celeste V0.1 BF16
Celeste · leafspark
Params70.6B
Context128K
Q4_K_M42.5 GB
RoleplayTool use
YI
Yi 1.5 9B Chat 16K Q5 K S
Yi · leafspark
Params8.83B
Context16K
Smallest6.1 GB
GGUF
LL
Meta Llama 3.1 8B Instruct Hf
Llama · leafspark
Params8.03B
Context128K
Smallest8.5 GB
GGUF
YI
Yi 1.5 9B Chat 16K Q6 K
Yi · leafspark
Params8.83B
Context16K
Smallest7.2 GB
GGUF
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Smallest24.3 GB
GGUF
YI
Yi 1.5 9B Chat 16K Q3 K M
Yi · leafspark
Params8.83B
Context16K
Smallest4.3 GB
GGUF
LL
Meta Llama 3.1 8B Instruct Hf
Llama · leafspark
Params8.03B
Context128K
Smallest6.6 GB
GGUF
LL
Meta Llama 3.1 8B Instruct
Llama · leafspark
Params8.03B
Context128K
Smallest3.2 GB
GGUF
YI
Yi-1.5-9B-Chat-16K
Yi · leafspark
Params8.83B
Context16K
Smallest5.1 GB
GGUF
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Q4_K_M20.7 GB
GGUF
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Smallest28.2 GB
GGUF
YI
Yi 1.5 9B Chat 16K Q5 K M
Yi · leafspark
Params8.83B
Context16K
Smallest6.3 GB
GGUF
YI
Yi-1.5-34B-Chat-16K
Yi · leafspark
Params34.4B
Context16K
Smallest12.8 GB
GGUF

About leafspark on Hugging Face

leafspark has published 36 GGUF models that ggufmodels.com tracks, across families such as Yi, Llama and Wikichat. The most downloaded are Llama 3.2 11B Vision Instruct, Llama-3-8B-Instruct-Gradient-4194k and Reflection Llama 3.1 70B.

The quants leafspark publishes most often are Q4_K_M (11), Q8_0 (9), Q2_K (9) and Q6_K (7). Their Q4_K_M files range from 4.1 to 50.7 GB. Parameter counts run from 121M to 218B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has leafspark published?

36 models are listed here, mainly from the Yi, Llama and Wikichat families. The most downloaded is Llama 3.2 11B Vision Instruct.

Which quants does leafspark publish?

The most common are Q4_K_M (11 models), Q8_0 (9 models), Q2_K (9 models) and Q6_K (7 models).

Keep browsing