Score 3GGUF
medgemma-1.5-4b-it-UD-Q8_K_XL
medgemma · Q8_K_XL · language
medicalsmall
4.81 GBFile size
6.5 GBVRAM fit
0Downloads
0Votes
Explore catalog
Top tested and selected AI LLM models.
Browse Hugston’s latest LLM models repository. Qwen3.6, Deepseek, GLM 4.7, LFM2.5, LLama3.3, Gemma4, Mistral, EuroLLM, Cybersec, Finetunes, Abliterated, Coderz, Vision...
Results
Use the forward/back controls to browse the next pages. Page state is kept with your current search and filters.
Score 3GGUF
eva-Financial Evasion Detection-4b-q8_0
eva · Q8_0 · language
financesmall
3.99 GBFile size
5.4 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
gpt-oss-20b-Coding-Distill.MXFP4
gpt · MXFP4 · language
general
12.85 GBFile size
17.3 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
AntAngelMed.i1-Q4_K_M
AntAngelMed · Q4_K_M · language
medical
58.14 GBFile size
78.5 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
TeichAIQwen3-4B-Thinking-2507-DeepSeek-v3.2-Speciale-Code-Distill.Q8_0
TeichAIQwen3 · Q8_0 · language
coderreasoningsmall
3.99 GBFile size
5.4 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
NousCoder-14B.q8_0
NousCoder · Q8_0 · language
codersmall
14.62 GBFile size
19.7 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Impish_Nemo_12B-Q8_0
Impish · Q8_0 · language
small
12.13 GBFile size
16.4 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hugston-code-rl-Qwen3-4B-Instruct-2507-SFT-30b-F32.Q8_0
Hugston · Q8_0 · language
coderhugstonlargesmall
3.99 GBFile size
5.4 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
10gb-data-30ba3b-distill-coder-4b-q8_0
10gb · Q8_0 · language
coderlargesmall
3.99 GBFile size
5.4 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
not-bad-qwen3-4b-opus-4.5-super-distll-exp-f16
not · F16 · language
small
7.5 GBFile size
10.1 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Java-sonar-notaccurate-oss-20b-MXFP4Q8_MOE
Java · Q8_MOE · language
general
11.28 GBFile size
15.2 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
TheDrummer_Cydonia-24B-v4.3-IQ4_NL
TheDrummer · IQ4_NL · language
largesmall
12.54 GBFile size
16.9 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hearthfire-24B-IQ4_NL
Hearthfire · IQ4_NL · language
largesmall
12.54 GBFile size
16.9 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Devstral-Small-2-24B-Instruct-2512-UD-Q4_K_XL
Devstral · Q4_K_XL · language
largesmall
13.51 GBFile size
18.2 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hugston-Qwen3-Coder-30B-A3B-Instruct-F32.IQ4_NL
Hugston · IQ4_NL · language
coderhugstonlargesmall
16.26 GBFile size
22 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
GLM-4.6V-Flash.Q8_0
GLM · Q8_0 · language
general
9.31 GBFile size
12.6 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
DeepSeek-R1-Cybersecurity-8B-Merged-f32.IQ4_NL
DeepSeek · IQ4_NL · language
reasoning
4.49 GBFile size
6.1 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
2dataset400mb-Medical-o1-Qwen3-Reasoning-4B.f16
2dataset400mb · F16 · language
medicalreasoningsmall
7.5 GBFile size
10.1 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hugston-code-rl-Qwen3-4B-Instruct-2507-SFT-30b-F32.IQ4_NL
Hugston · IQ4_NL · language
coderhugstonlargesmall
2.23 GBFile size
3 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Long-Hugston-code-rl-Qwen3-4B-Instruct-2507-SFT-30b-F32.IQ4_NL
Long · IQ4_NL · language
coderhugstonlargesmall
2.23 GBFile size
3 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hugston-therapist_model.Q8_0
Hugston · Q8_0 · language
hugston
7.95 GBFile size
10.7 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hugston-TroyDoesAIQwen3-15B-A2B-Base-f32.IQ4_NL
Hugston · IQ4_NL · language
hugstonsmall
8.33 GBFile size
11.2 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Qwen3-8B-gemini-3-pro-preview-high-reasoning-distill-Q8_0
8B · Q8_0 · language
reasoning
8.11 GBFile size
10.9 GBVRAM fit
0Downloads
0Votes
Score 3GGUF
Hugston-yarin-shakedQwen3-Codeforces-GRPO-f16
Hugston · F16 · language
coderhugston
1.12 GBFile size
2 GBVRAM fit
0Downloads
0Votes