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.
MI
Mistral 7b ITmodel
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
VI
vistral 7b chat
Vistral · tensorblock
Params7.29B
Context32K
Smallest2.7 GB
LL
Llama 160m
Llama · tensorblock
Params162M
Context2K
Smallest0.1 GB
QW
Qwen1.5 1.8B
Qwen · tensorblock
Params1.84B
Context32K
Smallest0.8 GB
QW
Qwen2.5 32B Instruct
Qwen · tensorblock
Params32.8B
Context32K
Smallest12.3 GB
DE
asm2asm deepseek1.3b xtokenizer arm
DeepSeek · tensorblock
Params1.35B
Context16K
Smallest0.6 GB
SE
ross dev sexyGPT Uncensored
Sexygpt · tensorblock
Params124M
Context1K
Smallest0.1 GB
LL
Mlx Community Llama 3.1 Nemotron 70B Instruct HF Bf16
Llama · tensorblock
Params70.6B
Context128K
Smallest26.4 GB
DE
Deepseek Ai Deepseek Coder 5.7bmqa Base
DeepSeek · tensorblock
Params5.7B
Context16K
Smallest2.1 GB
MA
MagicPrompt Stable Diffusion
Magicprompt · tensorblock
Params163M
Context1K
Smallest0.1 GB
AY
CohereForAI Aya Expanse 32b
Aya · tensorblock
Params32.3B
Context8K
Smallest12.8 GB
PR
prem 1B SQL
Prem · tensorblock
Params1.35B
Context16K
Smallest0.6 GB
TE
openGPT X Teuken 7B Instruct Commercial v0.4
Teuken · tensorblock
Params7.45B
Context4K
Smallest3.4 GB
MI
Mistral 7b
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
MI
MiniCPM 2B sft fp32
MiniCPM · tensorblock
Params2.72B
Context4K
Smallest1.2 GB
UN
Unsloth KernelLLM
Unsloth · tensorblock
Params8.03B
Context128K
Smallest3.2 GB
EX
experiment 45 intelligent layer 2 plus exp 39 data
Experiment · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
LE
Legmlai Legml v1.0 8b Instruct
Legml · tensorblock
Params8.19B
Context40K
Smallest3.3 GB
QW
QwQ 32B Snowdrop v0
Qwen · tensorblock
Params16M
Context128K
Smallest0.0 GB
MI
Dolphin 2.6 Mistral 7b Dpo
Mistral · tensorblock
Params7.24B
Context32K
Smallest2.7 GB
OL
Amd AMD OLMo 1B SFT DPO
OLMo · tensorblock
Params1.18B
Context2K
Smallest0.5 GB
ME
Langboat Mengzi3 8B Chat
Mengzi · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
WI
WizardLM 30B Uncensored Guanaco SuperCOT 30b
Wizardlm · tensorblock
Params32.5B
Context2K
Smallest12.0 GB
PO
polka 1.1b
Polka · tensorblock
Params1.15B
Context2K
Smallest0.5 GB
LL
Emotion LLaMA
Llama · tensorblock
Params6.74B
Context2K
Smallest2.5 GB
GR
Ibm Granite Granite 3b Code Instruct 2k
Granite · tensorblock
Params3.48B
Context2K
Smallest1.3 GB
AB
HuggingFaceFW Ablation Model Fineweb v1
Ablation · tensorblock
Params1.71B
Context2K
Smallest0.7 GB
MA
Anthracite Org Magnum v4 9b
Magnum · tensorblock
Params9.24B
Context8K
Smallest3.8 GB
LL
T3Q LLM Sft1.0 Dpo1.0
Llm · tensorblock
Params10.8B
Context4K
Smallest4.0 GB
QW
DavidAU Qwen3 30B A6B 16 Extreme
Qwen · tensorblock
Params30.5B
Context40K
Smallest11.3 GB