GGUF models by newsletter

56 GGUF models quantized by newsletter on Hugging Face. Sizes run from 596M to 46.7B parameters. The longest trained context is 1000K tokens.

Most downloadedNewestLargestLongest contextSmallest
PH
Phi 3 Medium 128k Instruct
Phi · newsletter
Params14B
Context128K
Smallest11.5 GB
Coding
PH
Phi 3 mini 128k instruct Q6 K
Phi · newsletter
Params3.82B
Context128K
Smallest3.1 GB
Coding
MI
CapybaraHermes 2.5 Mistral 7B Q6 K
Mistral · newsletter
Params7.24B
Context32K
Smallest5.9 GB
Tool use
OP
openchat 3.5 0106 Q6 K
Openchat · newsletter
Params7.24B
Context8K
Smallest5.9 GB
GGUF
HE
Hemmingway 1 Unlocked
Hemmingway · newsletter
Params934M
Context—
Smallest1.9 GB
GGUF
ZE
Zephyr 7b Beta
Zephyr · newsletter
Params7.24B
Context32K
Smallest5.9 GB
GGUF
MI
WizardLM 2 7B Q6 K
Microsoft · newsletter
Params7.24B
Context32K
Smallest5.9 GB
GGUF
PH
Phi 3.5 Mini Instruct
Phi · newsletter
Params3.82B
Context128K
Smallest3.1 GB
Coding
MI
Mistral 7B Instruct v0.3
Mistral · newsletter
Params7.25B
Context32K
Smallest5.9 GB
Tool use
CO
C4Ai Command R v01
Command R · newsletter
Params35B
Context128K
Q4_K_M21.5 GB
GGUF
NE
neural chat 7b v3 3 Q6 K
Neural · newsletter
Params7.24B
Context32K
Smallest5.9 GB
GGUF
ST
stablelm-2-zephyr-1_6b
Stablelm · newsletter
Params1.64B
Context4K
Smallest1.4 GB
GGUF
GR
granite 20b code instruct Q6 K
Granite · newsletter
Params20.1B
Context8K
Smallest16.5 GB
CodingTool use
MI
Mixtral-8x7B-Instruct-v0.1
Mistral · newsletter
Params46.7B
Context32K
Smallest38.4 GB
GGUF
MI
dolphin 2.8 mistral 7b v02 Q6 K
Mistral · newsletter
Params7.24B
Context32K
Smallest5.9 GB
CodingTool use
GR
granite-3b-code-instruct
Granite · newsletter
Params3.48B
Context2K
Smallest2.9 GB
CodingTool use
MI
Mini Magnum 12b v1.1
Mini · newsletter
Params12.2B
Context1000K
Smallest10.1 GB
GGUF
GE
Gemma 2 9b It
Gemma · newsletter
Params9.24B
Context8K
Smallest9.8 GB
GGUF
IN
Internlm2_5 7b Chat 1m
InternLM · newsletter
Params7.74B
Context256K
Smallest6.4 GB
GGUF
ST
Starling LM 7B beta Q6 K
Starling · newsletter
Params7.24B
Context8K
Smallest5.9 GB
GGUF
MI
Codestral 22B v0.1
Mistral · newsletter
Params22.2B
Context32K
Smallest23.6 GB
Coding
MI
dolphin 2.6 mistral 7b dpo Q6 K
Mistral · newsletter
Params7.24B
Context32K
Smallest5.9 GB
CodingTool use
TI
TinyLlama-1.1B-Chat-v1.0
Tinyllama · newsletter
Params1.1B
Context2K
Smallest0.9 GB
Coding
GE
Gemma 2 9B It SPPO Iter3
Gemma · newsletter
Params9.24B
Context8K
Smallest7.6 GB
GGUF
MI
dolphin-2.7-mixtral-8x7b
Mistral · newsletter
Params46.7B
Context32K
Smallest38.4 GB
CodingTool use
DI
DiscoLM_German_7b_v1
Discolm · newsletter
Params7.24B
Context32K
Smallest5.9 GB
GGUF
MI
Mistral Nemo Instruct 2407 Heretic v2
Mistral · newsletter
Params12.2B
Context128K
Smallest13.0 GB
Tool use
TO
ToriiGate v0.4 7B
Toriigate · newsletter
Params7.62B
Context32K
Smallest8.1 GB
Vision
GE
Gemma 2 9b It
Gemma · newsletter
Params9.24B
Context8K
Smallest7.6 GB
GGUF
MI
Mistral 7B Instruct v0.2
Mistral · newsletter
Params7.24B
Context32K
Smallest5.9 GB
GGUF

About newsletter on Hugging Face

newsletter has published 56 GGUF models that ggufmodels.com tracks, across families such as Mistral, Gemma and Phi. The most downloaded are Phi 3 Medium 128k Instruct, Phi 3 mini 128k instruct Q6 K and CapybaraHermes 2.5 Mistral 7B Q6 K.

The quants newsletter publishes most often are Q6_K (42), Q8_0 (13) and Q4_K_M (1). Their Q4_K_M files range from 21.5 to 21.5 GB. Parameter counts run from 596M to 46.7B, and the longest trained context window is 1000K tokens.

Frequently asked questions

What GGUF models has newsletter published?

56 models are listed here, mainly from the Mistral, Gemma and Phi families. The most downloaded is Phi 3 Medium 128k Instruct.

Which quants does newsletter publish?

The most common are Q6_K (42 models), Q8_0 (13 models) and Q4_K_M (1 models).

Keep browsing