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.
LL
Llama 3 13B Instruct
Llama · tensorblock
Params13B
Context8K
Smallest5.0 GB
LL
Crystalcareai Meta Llama 3.1 8b Instruct
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
MO
Monsoon-7B-exp-1
Monsoon · tensorblock
Params7.49B
Context32K
Smallest2.9 GB
QW
DavidAU Qwen3 8B 64k Context 2X Josiefied Uncensored
Qwen · tensorblock
Params8.19B
Context64K
Smallest3.3 GB
LL
Bohanlu Taigi Llama 2 Translator 7B
Llama · tensorblock
Params6.94B
Context4K
Smallest2.6 GB
DE
Deepseek Ai Deepseek Coder 1.3b Instruct
DeepSeek · tensorblock
Params1.35B
Context16K
Smallest0.6 GB
MX
Mxbai Rerank Large v2
Mxbai · tensorblock
Params1.54B
Context32K
Smallest0.7 GB
QV
Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r
Qvikhr · tensorblock
Params1.54B
Context32K
Smallest0.7 GB
DI
dictalm2.0 instruct fine tuned
Dictalm · tensorblock
Params7.25B
Context32K
Smallest2.7 GB
LD
LDCC SOLAR gugutypus 10.7B
Ldcc · tensorblock
Params10.9B
Context4K
Smallest4.1 GB
WE
Wernicke 7B v8
Wernicke · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
JS
JSL MedLlama 3 8B v1.0
Jsl · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
SA
Sail Sailor 0.5B
Sailor · tensorblock
Params620M
Context32K
Smallest0.3 GB
LL
Llama 3.1 8B Lexi Uncensored V2
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
LL
Hfl Llama 3 Chinese 8b
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
QW
Qwen Qwen1.5 7B
Qwen · tensorblock
Params7.72B
Context32K
Smallest3.1 GB
OL
Allenai OLMoE 1B 7B 0924 Instruct
OLMo · tensorblock
Params6.92B
Context4K
Smallest2.6 GB
DE
Mlx Community DeepSeek R1 Distill Qwen 14B
DeepSeek · tensorblock
Params14.8B
Context128K
Smallest5.8 GB
MI
MNCJ1hun Mistral 7B OP u1k ver0.4
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
PH
Huihui Ai Phi 4 Mini Instruct Abliterated
Phi · tensorblock
Params3.84B
Context128K
Smallest1.7 GB
QW
Qwen Qwen3 14B
Qwen · tensorblock
Params14.8B
Context40K
Smallest5.8 GB
CO
CodeSteer v1
Codesteer · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
DE
DeepSeek R1 Distill Qwen 1.5B
DeepSeek · tensorblock
Params1.78B
Context128K
Smallest0.8 GB
LL
LumiOpen Llama Poro 2 8B Instruct
Llama · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
QW
Qwen Qwen3 Reranker 4B
Qwen · tensorblock
Params4.02B
Context40K
Smallest1.7 GB
MI
MistralLite
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
LL
Mims Harvard TxAgent T1 Llama 3.1 8B
Llama · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
MA
Marco o1
Marco · tensorblock
Params7.62B
Context32K
Smallest3.0 GB
RA
rank zephyr 7b v1 full
Rank · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
QW
Qwen Qwen2.5 7B Instruct
Qwen · tensorblock
Params7.62B
Context32K
Smallest3.0 GB