GGUF models by grimjim

38 GGUF models quantized by grimjim on Hugging Face. Sizes run from 7.24B to 23.6B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
Llama 3.1 8B Instruct Abliterated_Via_Adapter
Llama · grimjim
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
MA
Magnolia Mell v1 12B
Magnolia · grimjim
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
CU
cuckoo starling 32k 7B
Cuckoo · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MO
grimjim_Modicum Of Doubt v1 24B
Modicum · grimjim
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
LL
Llama Nephilim Metamorphosis v1 8B
Llama · grimjim
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
KU
kukulemon spiked 9B
Kukulemon · grimjim
Params8.99B
Context8K
Q4_K_M5.4 GB
GGUF
RO
rogue-enchantress-32k-7B
Rogue · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
Llama 3 Luminurse v0.1 OAS 8B
Llama · grimjim
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
ZE
zephyr-wizard-kuno-royale-BF16-merge-7B
Zephyr · grimjim
Params7.24B
Context32K
Smallest4.4 GB
GGUF
KU
kuno kunoichi v1 DPO v2 SLERP 7B
Kuno · grimjim
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF
MA
grimjim_Magrathic 12B
Magrathic · grimjim
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
KU
kukulemon v3 soul mix 32k 7B
Kukulemon · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
KU
kunoichi-lemon-royale-v3-32K-7B
Kunoichi · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
llama 3 experiment v1 9B
Llama · grimjim
Params8.9B
Context8K
Q4_K_M5.4 GB
GGUF
GE
gemma 3 12b it abliterated
Gemma · grimjim
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
KU
kukulemon 32K 7B
Kukulemon · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
llama 3 Nephilim v1 8B
Llama · grimjim
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
LL
llama 3 Nephilim v3 8B
Llama · grimjim
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
KU
kunoichi lemon royale v2 32K 7B
Kunoichi · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
llama 3 Nephilim v2 8B
Llama · grimjim
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Kitsunebi v1 Gemma2 8k 9B
Gemma · grimjim
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
KU
kukulemon 7B
Kukulemon · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
FI
fireblossom 32K 7B
Fireblossom · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
MA
grimjim_madwind-wizard-7B
Madwind · grimjim
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LL
llama 3 Nephilim v2.1 8B
Llama · grimjim
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Magot v1 Gemma2 8k 9B
Gemma · grimjim
Params9.24B
Context8K
Q4_K_M5.8 GB
GGUF
MA
Magnolia V3B 12B
Magnolia · grimjim
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
LE
lemonade rebase 32k 7B
Lemonade · grimjim
Params7.24B
Context32K
Smallest7.7 GB
GGUF
MA
grimjim_MagTie v1 12B
Magtie · grimjim
Params12.2B
Context128K
Q4_K_M7.5 GB
GGUF
KU
kunoichi lemon royale 7B
Kunoichi · grimjim
Params7.24B
Context8K
Q4_K_M4.4 GB
GGUF

About grimjim on Hugging Face

grimjim has published 38 GGUF models that ggufmodels.com tracks, across families such as Llama, Kukulemon and Gemma. The most downloaded are Llama 3.1 8B Instruct Abliterated_Via_Adapter, Magnolia Mell v1 12B and cuckoo starling 32k 7B.

The quants grimjim publishes most often are Q8_0 (37), Q6_K (34), Q5_K_M (34) and Q4_K_M (34). Their Q4_K_M files range from 4.4 to 14.3 GB. Parameter counts run from 7.24B to 23.6B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has grimjim published?

38 models are listed here, mainly from the Llama, Kukulemon and Gemma families. The most downloaded is Llama 3.1 8B Instruct Abliterated_Via_Adapter.

Which quants does grimjim publish?

The most common are Q8_0 (37 models), Q6_K (34 models), Q5_K_M (34 models) and Q4_K_M (34 models).

Keep browsing