Sft GGUF models

115 GGUF models in the Sft family, quantized by 17 uploaders. Sizes run from 21M to 32.8B parameters. The longest trained context is 1000K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
SF
MT7Bi sft i1
Sft · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
SF
0810 SFT Github Orlm Industryor 14B 5e 6 64
Sft · mradermacher
Params14.8B
Context40K
Q4_K_M9.0 GB
ReasoningTool use
SF
Sft_Subtitles_Fixer_V1_Merged
Sft · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
GGUF
SF
sft v1 q4km
Sft · Ha-Te-21
Params7.46B
Context128K
Smallest5.3 GB
GGUF
SF
SFT RL SynergyDilemma RL
Sft · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
Tool useVision
SF
SFT 4B ScaleCUA MixedOpen
Sft · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool useVision
SF
SFT RL SynergyDilemma SFT_s1.1_R1
Sft · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningTool useVision
SF
sft apps ds 7b inst
Sft · mradermacher
Params6.91B
Context4K
Q4_K_M4.2 GB
GGUF
SF
G4 26B SFT v2 1 GRPO chkpt40 MT PlainSFT ck75 TU
Sft · ApocalypseParty
Params25.2B
Context256K
Smallest22.6 GB
ReasoningTool use
SF
aryolotfi/SFT_gsm8k_rho-math-1b-v0.1_epoch_2_global_step_58
Sft · featherless-ai-quants
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
SF
skarnam/SFT_fft_DARE_Resta
Sft · featherless-ai-quants
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
SF
aryolotfi/SFT_gsm8k_rho-math-1b-v0.1_epoch_3_global_step_87
Sft · featherless-ai-quants
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
SF
SFT MedLLama Nachos 13b
Sft · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
SF
iw SFT 32B i1
Sft · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
SF
SFT MedLLama 13B
Sft · mradermacher
Params13B
Context2K
Q4_K_M7.9 GB
GGUF
SF
Sft_Subtitles_Fixer_V1_Merged
Sft · mradermacher
Params11.8B
Context128K
Q4_K_M7.3 GB
Vision
SF
rp sft merged 1000
Sft · AiAF
Params2.61B
Context8K
Q4_K_M1.7 GB
Roleplay
SF
iw SFT 32B
Sft · mradermacher
Params32.8B
Context32K
Q4_K_M19.9 GB
Tool use
SF
aryolotfi/SFT_gsm8k_rho-math-1b-v0.1_epoch_5_global_step_145
Sft · featherless-ai-quants
Params1.1B
Context2K
Q4_K_M0.7 GB
GGUF
SF
G4 26B SFT v3
Sft · ApocalypseParty
Params25.2B
Context256K
Smallest22.6 GB
ReasoningTool use
SF
sft solar 10.7b v1
Sft · tensorblock
Params10.7B
Context4K
Smallest4.0 GB
GGUF
SF
G4 26B SFT v2 1 GRPO chkpt40 MT PlainSFT ck75
Sft · ApocalypseParty
Params25.2B
Context256K
Smallest22.6 GB
ReasoningTool use
SF
MT7Bi sft
Sft · mradermacher
Params6.74B
Context2K
Q4_K_M4.1 GB
GGUF
SF
Yi Ko SFT FULL
Sft · RichardErkhov
Params6.18B
Context2K
Q4_K_M3.8 GB
GGUF
SF
SFT 4B ScaleCUA EvoCUA
Sft · prithivMLmods
Params4.02B
Context256K
Q4_K_M2.5 GB
Tool useVision
SF
Sft_Banking_Model
Sft · Akhenaton
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
SF
sft_quantum_circuit_gen_8B
Sft · mradermacher
Params8.19B
Context40K
Q4_K_M5.0 GB
ReasoningTool use
SF
sft ds 140k
Sft · tensorblock
Params8.03B
Context8K
Smallest3.2 GB
GGUF
SF
G4 26B SFT v2 1 GRPO chkpt40 MV
Sft · ApocalypseParty
Params25.2B
Context256K
Smallest22.8 GB
ReasoningTool use
SF
SFT airline
Sft · alansu7
Params12.2B
Context1000K
Smallest24.5 GB
Tool use

About the Sft GGUF models

Sft is represented on ggufmodels.com by 115 GGUF models, quantized by 17 uploaders on Hugging Face. The most downloaded are MT7Bi sft i1, 0810 SFT Github Orlm Industryor 14B 5e 6 64 and Sft_Subtitles_Fixer_V1_Merged. Parameter counts run from 21M to 32.8B, and the longest trained context window is 1000K tokens.

A Q4_K_M file of a Sft model is between 0.1 to 19.9 GB, which is the quant most people start with. Most files come from mradermacher (32), ApocalypseParty (23) and Andrei1980 (16). The quants you will meet most often are Q8_0 (63), Q4_K_M (60), Q2_K (60) and Q6_K (54), where the number is how many models offer that quant.

Frequently asked questions

Which Sft GGUF should I download?

The most downloaded Sft GGUF here is MT7Bi sft i1. Pick the size that fits your GPU first, then choose a quant: Q4_K_M is the usual starting point, and Q5_K_M or Q6_K give more quality if you have memory to spare. The VRAM pages below list what fits each GPU.

How much VRAM does a Sft model need?

Q4_K_M files of Sft models on this site range from 0.1 to 19.9 GB. Add the KV cache for your context length and about 0.5 GB for the runtime, which usually means 1.5 to 3 GB on top of the file at an 8K context.

Where do Sft GGUF files come from?

The most common quantizers here are mradermacher, ApocalypseParty and Andrei1980. They convert the original model and publish quantized files on Hugging Face. ggufmodels.com does not host files; every download button opens Hugging Face.

Keep browsing