GGUF models by Melvin56

62 GGUF models quantized by Melvin56 on Hugging Face. Sizes run from 494M to 10.3B parameters. The longest trained context is 128K tokens.

Most downloadedNewestLargestLongest contextSmallest
DE
DeepSeek R1 Distill Qwen 7B Abliterated v2
DeepSeek · Melvin56
Params7.62B
Context128K
Q4_K_M4.7 GB
Reasoning
PH
Phi 4 Mini Instruct Abliterated
Phi · Melvin56
Params3.84B
Context128K
Q4_K_M2.5 GB
Coding
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · Melvin56
Params7.62B
Context32K
Q4_K_M4.7 GB
CodingTool use
QW
Qwen3 4B
Qwen · Melvin56
Params4.02B
Context40K
Smallest2.2 GB
ReasoningTool use
QW
Qwen3 1.7B Abliterated
Qwen · Melvin56
Params1.72B
Context40K
Q4_K_M1.1 GB
GGUF
GL
GLM 4 9B 0414 Abliterated
GLM · Melvin56
Params9.4B
Context32K
Q4_K_M6.2 GB
Tool use
QW
Qwen3 8B Abliterated
Qwen · Melvin56
Params8.19B
Context40K
Q4_K_M5.0 GB
GGUF
QW
Qwen3 4B Abliterated
Qwen · Melvin56
Params4.02B
Context40K
Q4_K_M2.5 GB
GGUF
DE
DeepScaleR 1.5B Preview
Deepscaler · Melvin56
Params1.78B
Context128K
Q4_K_M1.1 GB
Tool use
GL
GLM 4 9B 0414
GLM · Melvin56
Params9.4B
Context32K
Q4_K_M6.2 GB
Tool use
PH
Phi 4 Mini Instruct
Phi · Melvin56
Params3.84B
Context128K
Q4_K_M2.5 GB
CodingTool use
GL
GLM Z1 9B 0414 Abliterated
GLM · Melvin56
Params9.4B
Context32K
Q4_K_M6.2 GB
Tool use
KO
ko r1 7b v2.0.3
Melvin56
Params7.61B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
DE
DeepSeek R1 ReDistill Qwen 7B v1.1
DeepSeek · Melvin56
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
GL
GLM Z1 9B 0414
GLM · Melvin56
Params9.4B
Context32K
Q4_K_M6.2 GB
Tool use
HA
Hammer2.1 3b
Hammer · Melvin56
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
HA
Hammer2.1 0.5b
Hammer · Melvin56
Params494M
Context32K
Q4_K_M0.4 GB
CodingTool use
UI
UIGEN T2 7B
Uigen · Melvin56
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · Melvin56
Params7.62B
Context32K
Smallest4.2 GB
CodingTool use
EL
Elita 0.1 Distilled R1 Abliterated
Elita · Melvin56
Params7.62B
Context128K
Q4_K_M4.7 GB
ReasoningTool use
LL
Hermes 3 Llama 3.2 3B
Llama · Melvin56
Params3.21B
Context128K
Smallest1.9 GB
RoleplayTool use
QW
Qwen2.5 7B Instruct Abliterated v3
Qwen · Melvin56
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
DR
Dria Agent A 3B Abliterated
Dria · Melvin56
Params3.09B
Context32K
Q4_K_M1.9 GB
CodingTool use
KA
Kanana Nano 2.1b Instruct Abliterated
Kanana · Melvin56
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF
LL
Nidum Llama 3.2 3B Uncensored
Llama · Melvin56
Params3.21B
Context128K
Q4_K_M2.0 GB
CodingTool use
QW
Qwen3 0.6B Abliterated
Qwen · Melvin56
Params596M
Context40K
Q4_K_M0.4 GB
GGUF
QW
Qwen2.5 Coder 7B Instruct Abliterated
Qwen · Melvin56
Params7.62B
Context32K
Smallest8.1 GB
CodingTool use
DE
DeepSeek R1 ReDistill Qwen 1.5B v1.1
DeepSeek · Melvin56
Params1.78B
Context128K
Q4_K_M1.1 GB
ReasoningTool use
KA
Kanana Nano 2.1b Instruct
Kanana · Melvin56
Params2.09B
Context8K
Q4_K_M1.4 GB
GGUF
HA
Hammer2.1 7b
Hammer · Melvin56
Params7.61B
Context32K
Q4_K_M4.7 GB
CodingTool use

About Melvin56 on Hugging Face

Melvin56 has published 62 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Hammer. The most downloaded are DeepSeek R1 Distill Qwen 7B Abliterated v2, Phi 4 Mini Instruct Abliterated and Qwen2.5 Coder 7B Instruct Abliterated.

The quants Melvin56 publishes most often are Q8_0 (36), Q4_K_M (33), Q2_K (28) and Q5_K_M (26). Their Q4_K_M files range from 0.4 to 6.2 GB. Parameter counts run from 494M to 10.3B, and the longest trained context window is 128K tokens.

Frequently asked questions

What GGUF models has Melvin56 published?

62 models are listed here, mainly from the Qwen, Llama and Hammer families. The most downloaded is DeepSeek R1 Distill Qwen 7B Abliterated v2.

Which quants does Melvin56 publish?

The most common are Q8_0 (36 models), Q4_K_M (33 models), Q2_K (28 models) and Q5_K_M (26 models).

Keep browsing