Chat GGUF models

88 GGUF models in the Chat family, quantized by 31 uploaders. Sizes run from 121M to 65.3B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
CH
CarbonGPT
Chat · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
CH
Chat_Noir
Chat · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
CH
Chat_Noir 24b v2
Chat · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
CH
Chat_Noir 24b v3
Chat · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
CH
K2 Chat i1
Chat · mradermacher
Params65.3B
Context8K
Q4_K_M39.3 GB
GGUF
CH
K2-Chat
Chat · legraphista
Params65.3B
Context8K
Smallest14.2 GB
GGUF
CH
Chat2DB SQL 7B
Chat · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
CH
Chat_Noir
Chat · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
CH
Chat Kto Vision
Chat · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
Tool useVision
CH
K2 Chat
Chat · RichardErkhov
Params65.3B
Context8K
Q4_K_M39.3 GB
GGUF
CH
chat
Chat · gguf-org
Params1B
Context32K
Smallest0.7 GB
GGUF
CH
chat GPT2
Chat · mradermacher
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
CH
Chat_Gpt2
Chat · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
CH
Chat bit 1.7B Quant
Chat · netizen4-bit
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
CH
Chat 24b
Chat · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
CH
Chat KTO
Chat · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
CH
Chat_Noir 24b v2
Chat · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
CH
K2 Chat
Chat · mradermacher
Params65.3B
Context8K
Q4_K_M39.3 GB
GGUF
CH
Chat 24b
Chat · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
CH
Chat2Find Sinhala Translator 4B
Chat · mradermacher
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
CH
Chat KTO
Chat · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
CH
Chat Doctor i1
Chat · mradermacher
Params494M
Context128K
Q4_K_M0.4 GB
GGUF
CH
Chat_Noir 24b v3
Chat · mradermacher
Params23.6B
Context32K
Q4_K_M14.3 GB
GGUF
CH
Chat2DB-SQL-7B
Chat · bartowski
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF
CH
chat doctor v2
Chat · mradermacher
Params6.74B
Context4K
Q4_K_M4.1 GB
GGUF
CH
chat gpt2
Chat · tensorblock
Params121M
Context1K
Smallest0.1 GB
GGUF
CH
Chat E4 1e5
Chat · mradermacher
Params23.6B
Context128K
Q4_K_M14.3 GB
GGUF
CH
AR 8B Chat
Chat · mradermacher
Params8.19B
Context32K
Q4_K_M5.0 GB
ReasoningTool use
CH
AR 4B Chat
Chat · mradermacher
Params4.41B
Context32K
Q4_K_M2.7 GB
ReasoningTool use
CH
Chat2DB SQL 7B
Chat · mradermacher
Params6.74B
Context16K
Q4_K_M4.1 GB
GGUF

About the Chat GGUF models

Chat is represented on ggufmodels.com by 88 GGUF models, quantized by 31 uploaders on Hugging Face. The most downloaded are CarbonGPT, Chat_Noir and Chat_Noir 24b v2. Parameter counts run from 121M to 65.3B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Chat model is between 0.1 to 39.3 GB, which is the quant most people start with. Most files come from mradermacher (39), luckycanucky (6) and RichardErkhov (4). The quants you will meet most often are Q4_K_M (62), Q2_K (59), Q5_K_M (57) and Q3_K_M (55), where the number is how many models offer that quant.

Frequently asked questions

Which Chat GGUF should I download?

The most downloaded Chat GGUF here is CarbonGPT. 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 Chat model need?

Q4_K_M files of Chat models on this site range from 0.1 to 39.3 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 Chat GGUF files come from?

The most common quantizers here are mradermacher, luckycanucky and RichardErkhov. 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