GGUF models by Guilherme34

89 GGUF models quantized by Guilherme34 on Hugging Face. Sizes run from 4M to 406B parameters. The longest trained context is 256K tokens.

Most downloadedNewestLargestLongest contextSmallest
ME
Medra4b Abliterated
Medra · Guilherme34
Params4.55B
Context128K
Q4_K_M2.9 GB
ReasoningVision
QW
Qwen_Qwen3.5 9B__project Jeva 9b_1791678248
Qwen · Guilherme34
Params9.08B
Context256K
Q4_K_M5.7 GB
ReasoningTool useVision
FI
Firefly v4
Firefly · Guilherme34
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningRoleplayTool use
LF
LFM3 1.7B Looped HiddenCoT
Lfm · Guilherme34
Params2.7B
Context256K
Smallest2.2 GB
ReasoningTool use
FI
Firefly v4
Firefly · Guilherme34
Params4.65B
Context128K
Q4_K_M3.4 GB
ReasoningRoleplayTool use
TW
TwIL 8B Abliterated Uncensored
Twil · Guilherme34
Params8.79B
Context128K
Smallest9.3 GB
GGUF
NA
S5 Nano Uncensored
Nano · Guilherme34
Params4.33B
Context256K
Smallest4.6 GB
ReasoningTool use
SA
Samantha vision v2
Samantha · Guilherme34
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool useVision
NA
S5 Nano Uncensored
Nano · Guilherme34
Params4.33B
Context256K
Smallest3.6 GB
ReasoningTool use
QW
Qwen2.5 14B Instruct
Qwen · Guilherme34
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
GP
GPT OSS UNCENSORED 20B
gpt-oss · Guilherme34
Params20.9B
Context128K
Smallest12.4 GB
Tool use
QW
Qwen2.5 14B Instruct
Qwen · Guilherme34
Params14.8B
Context32K
Smallest15.7 GB
Tool use
FI
Firefly V2Q Think RP
Firefly · Guilherme34
Params4.21B
Context256K
Q4_K_M2.7 GB
ReasoningRoleplayVision
SA
Samantha Mythomax l2 13b merge fixed Q3 K S
Samantha · Guilherme34
Params13B
Context4K
Smallest5.7 GB
GGUF
SA
Samantha OSONE 7b
Samantha · Guilherme34
Params6.74B
Context4K
Smallest7.2 GB
GGUF
SA
Samantha 3b Beta0.1 Model
Samantha · Guilherme34
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
SA
Samantha Mythomax l2 13b merge fixed Q3 K L
Samantha · Guilherme34
Params13B
Context4K
Smallest6.9 GB
GGUF
SA
Samantha vision
Samantha · Guilherme34
Params7.24B
Context32K
Smallest7.7 GB
Vision
SA
Samantha test Q4 K M
Samantha · Guilherme34
Params8.03B
Context128K
Q4_K_M4.9 GB
Tool useVision
PS
Psychologist 3b GGUF Q4 K M
Psychologist · Guilherme34
Params3.21B
Context128K
Q4_K_M2.0 GB
Tool use
QW
Samantha Qwen 0.5b
Qwen · Guilherme34
Params494M
Context32K
Smallest0.5 GB
GGUF
FI
Firefly V2
Firefly · Guilherme34
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
FI
Firefly v5 Beta
Firefly · Guilherme34
Params4.65B
Context128K
Smallest5.0 GB
ReasoningTool useVision
FI
Firefly V3.2 Alpha
Firefly · Guilherme34
Params3.21B
Context128K
Smallest3.4 GB
Roleplay
FI
Firefly V2.5
Firefly · Guilherme34
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
SA
Samantha Mythomax l2 13b merge fixed Q2 K
Samantha · Guilherme34
Params13B
Context4K
Smallest4.9 GB
GGUF
GP
Gptossuncensor
gpt-oss · Guilherme34
Params4M
Context—
Smallest0.0 GB
GGUF
SA
Samantha Mythomax l2 13b merge fixed Q4 K M
Samantha · Guilherme34
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
MI
MiniAGI Selfimprove
Miniagi · Guilherme34
Params7.62B
Context32K
Smallest8.1 GB
Tool use
MA
Maya Q4 K M
Maya · Guilherme34
Params3.3B
Context128K
Q4_K_M2.1 GB
Tool use

About Guilherme34 on Hugging Face

Guilherme34 has published 89 GGUF models that ggufmodels.com tracks, across families such as Samantha, Firefly and Qwen. The most downloaded are Medra4b Abliterated, Qwen_Qwen3.5 9B__project Jeva 9b_1791678248 and Firefly v4.

The quants Guilherme34 publishes most often are Q4_K_M (32), Q8_0 (22), Q6_K (15) and Q2_K (9). Their Q4_K_M files range from 0.8 to 243.1 GB. Parameter counts run from 4M to 406B, and the longest trained context window is 256K tokens.

Frequently asked questions

What GGUF models has Guilherme34 published?

89 models are listed here, mainly from the Samantha, Firefly and Qwen families. The most downloaded is Medra4b Abliterated.

Which quants does Guilherme34 publish?

The most common are Q4_K_M (32 models), Q8_0 (22 models), Q6_K (15 models) and Q2_K (9 models).

Keep browsing