GGUF models by tensorblock

4944 GGUF models quantized by tensorblock on Hugging Face. Sizes run from 1M to 72.7B parameters. The longest trained context is 1024K tokens.

Most downloadedNewestLargestLongest contextSmallest
MI
MistralLite 11B
Mistral · tensorblock
Params10.7B
Context32K
Smallest4.0 GB
GGUF
GP
Gpt2 Large
Gpt · tensorblock
Params774M
Context1K
Smallest0.3 GB
GGUF
MO
Moonlight L3 15B v2 64k
Moonlight · tensorblock
Params15B
Context64K
Smallest5.7 GB
GGUF
TW
Twice KoSOLAR 16.1B test
Twice · tensorblock
Params16.1B
Context4K
Smallest6.0 GB
GGUF
AR
Artigenz Coder DS 6.7B
Artigenz · tensorblock
Params6.74B
Context16K
Smallest2.5 GB
Coding
WI
WizardLM 2 7B abliterated
Wizardlm · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
TI
Tifa Deepsex 14b CoT
Tifa · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
RoleplayTool use
RA
Rank_Vicuna_7B_V1_Fp16
Rank · tensorblock
Params6.74B
Context4K
Smallest2.5 GB
Embedding
LI
ds-limo-fr-250
Limo · tensorblock
Params7.62B
Context128K
Smallest3.0 GB
ReasoningTool use
LL
Mlx Community Hermes 3 Llama 3.2 3B Bf16
Llama · tensorblock
Params3.21B
Context128K
Smallest1.4 GB
RoleplayTool use
AR
Arcee Spark
Arcee · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
GGUF
CA
CarbonVillain En 10.7B v2
Carbonvillain · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
KE
Obrolin Kesehatan 7B v0.1
Kesehatan · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
LL
llama2 13b v0.1
Llama · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
SN
sn29 v33
tensorblock
Params6.88B
Context4K
Smallest2.9 GB
GGUF
TI
Tifa DeepsexV2 7b MGRPO GGUF F16
Tifa · tensorblock
Params7.62B
Context986K
Smallest3.0 GB
RoleplayTool use
YU
YuE s1 7B anneal jp kr icl
Yue · tensorblock
Params6.22B
Context16K
Smallest2.4 GB
GGUF
NE
CultriX NeuralTrix 7B dpo
Neuraltrix · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
LL
llama2 merge v0.3
Llama · tensorblock
Params13.2B
Context2K
Smallest4.9 GB
GGUF
PO
polka 1.1b chat
Polka · tensorblock
Params1.15B
Context4K
Smallest0.5 GB
GGUF
LL
Yaojialzc Gigi Llama3 8B Chinese Zh
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
Tool use
MH
Mhm 7b v1.3
Mhm · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
TO
Unbabel TowerInstruct 13B v0.1
Towerinstruct · tensorblock
Params13B
Context4K
Smallest4.9 GB
GGUF
GR
Ibm Granite Granite 3.1 3b A800M Base
Granite · tensorblock
Params3.3B
Context128K
Smallest1.2 GB
GGUF
FU
FusionNet_34Bx2_MoE
Fusionnet · tensorblock
Params60.8B
Context32K
Smallest22.4 GB
GGUF
DA
DataVortexS 10.7B Dpo v1.6
Datavortexs · tensorblock
Params10.9B
Context4K
Smallest4.1 GB
GGUF
TI
Tinyllama
Tinyllama · tensorblock
Params1.1B
Context2K
Smallest0.4 GB
GGUF
MI
Mistral 7B Base SFT SimPO
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
GGUF
OP
Nectec OpenThaiLLM Prebuilt 7B
Openthaillm · tensorblock
Params7.62B
Context128K
Smallest3.0 GB
CodingTool use
LL
Llama 3.1 SuperNova 8B Lite TIES with Base
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
GGUF

Keep browsing