Fine GGUF models

83 GGUF models in the Fine family, quantized by 45 uploaders. Sizes run from 9M to 14.8B parameters. The longest trained context is 256K tokens.

TinySmallMediumLarge
Most downloadedNewestLargestLongest contextSmallest
FI
Fine R1 7B
Fine · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
FI
Fine R1 7B
Fine · mradermacher
Params7.62B
Context125K
Q4_K_M4.7 GB
ReasoningVision
FI
Fine R1 3B
Fine · mradermacher
Params3.4B
Context125K
Q4_K_M2.1 GB
ReasoningTool useVision
FI
Fine R1 3B
Fine · mradermacher
Params3.4B
Context125K
Q4_K_M2.1 GB
ReasoningTool useVision
FI
Fine R1 3B Final Model
Fine · mradermacher
Params3.4B
Context125K
Q4_K_M2.1 GB
ReasoningVision
FI
Fine Tuned Merged Model
Fine · RichardErkhov
Params1.24B
Context128K
Q4_K_M0.8 GB
GGUF
FI
Fine_Tuned_Model
Fine · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
FI
fine tuned text to sql codegemma 7b v0.2 GGUF q4 k m
Fine · Fduv
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
FI
fine tuned text to sql codegemma 7b v0.1 GGUF q4 k m
Fine · Fduv
Params8.54B
Context8K
Q4_K_M5.3 GB
GGUF
FI
fine tune llm
Fine · NotCis07
Params1.54B
Context32K
Q4_K_M1.0 GB
Tool use
FI
Fine_Tuned_Gpt2
Fine · RichardErkhov
Params163M
Context1K
Q4_K_M0.1 GB
GGUF
FI
Fine Tune Llma 3.1 8b Math
Fine · seharn
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF
FI
Fine Lightning 14b
Fine · mradermacher
Params14.8B
Context32K
Q4_K_M9.0 GB
GGUF
FI
fine tuned lora model
Fine · leopoldh
Params1.24B
Context128K
Q4_K_M0.8 GB
Tool use
FI
fine tuned fire model Q8 0
Fine · salni84
Params1.24B
Context128K
Smallest1.3 GB
Tool use
FI
Fine tuneLLM VSTEP
Fine · PeterFostream
Params3.21B
Context128K
Smallest3.4 GB
Tool use
FI
fine tuned model
Fine · ashercn97
Params7.62B
Context128K
Q4_K_M4.7 GB
GGUF
FI
fine4model
Fine · giayphuyen
Params3.21B
Context128K
Smallest3.4 GB
Tool use
FI
kg to fine v1
Fine · Hyuk0816
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningTool useVision
FI
fine tuning 42
Fine · harissonduraes
Params1.94B
Context256K
Q4_K_M1.3 GB
ReasoningTool useVision
FI
Fine Tune Ollama Test v1
Fine · VietAnh12468
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
FI
fine tuning
Fine · sx666
Params8.03B
Context128K
Smallest8.5 GB
ReasoningTool use
FI
fine tuned unit test generator
Fine · nihardon
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
FI
fine tuneq8
Fine · Incorrect12321
Params8.03B
Context128K
Smallest8.5 GB
GGUF
FI
Fine Tune 720_UP_Dataset
Fine · Kittigon
Params3.21B
Context128K
Smallest3.4 GB
Tool use
FI
fine tuning nurd
Fine · Makesols
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool use
FI
Fine Tuned Fire Model
Fine · salni84
Params9M
Context—
Smallest0.0 GB
GGUF
FI
Fine_Tuned_Iris
Fine · Open-SLMproject
Params1.1B
Context2K
Smallest2.2 GB
GGUF
FI
Fine Tuning 27
Fine · harissonduraes
Params3.21B
Context128K
Smallest6.4 GB
Tool use
FI
Fine_Tuned_Model
Fine · akshay204
Params8.03B
Context128K
Q4_K_M4.9 GB
GGUF

About the Fine GGUF models

Fine is represented on ggufmodels.com by 83 GGUF models, quantized by 45 uploaders on Hugging Face. The most downloaded are Fine R1 7B, Fine R1 7B and Fine R1 3B. Parameter counts run from 9M to 14.8B, and the longest trained context window is 256K tokens.

A Q4_K_M file of a Fine model is between 0.1 to 9.0 GB, which is the quant most people start with. Most files come from harissonduraes (21), mradermacher (7) and giayphuyen (5). The quants you will meet most often are Q8_0 (45), Q4_K_M (42), Q5_K_M (15) and Q3_K_S (12), where the number is how many models offer that quant.

Frequently asked questions

Which Fine GGUF should I download?

The most downloaded Fine GGUF here is Fine R1 7B. 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 Fine model need?

Q4_K_M files of Fine models on this site range from 0.1 to 9.0 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 Fine GGUF files come from?

The most common quantizers here are harissonduraes, mradermacher and giayphuyen. 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