Csaba Kecskemeti PRO

csabakecskemeti's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in DevQuasar/amd.Instella-MoE-16B-A3B-Think-GGUF 15 days ago

[BUG] Instella-MoE-16B-A3B GGUF generates garbage output on both CPU and CUDA?

2

#1 opened about 2 months ago by

BobbyLLM

New activity in meta-models/Muse-Glimmer-30B 2 months ago

5090 dflash results - can you share details?

4

#21 opened 2 months ago by

csabakecskemeti

New activity in Qwen/Qwen-Image-Bench 3 months ago

why not in base llama.cpp?

1

#2 opened 3 months ago by

kalle07

New activity in InternScience/Agents-A1 3 months ago

Update README.md

#29 opened 3 months ago by

csabakecskemeti

please update pipeline_tag to image-text-to-text

#28 opened 3 months ago by

csabakecskemeti

New activity in DevQuasar/Qwen.Qwen-AgentWorld-35B-A3B-GGUF 4 months ago

llama.cpp crash: missing tensor 'blk.40.attn_norm.weight' (Incorrect GGUF Metadata)

🤝 1

2

#1 opened 4 months ago by

freykun

New activity in DevQuasar/CohereLabs.command-a-plus-05-2026-bf16-GGUF-EXPERIMENTAL 4 months ago

Wrongly made GGUF

2

#1 opened 4 months ago by

Nerdsking

New activity in DevQuasar/zai-org.GLM-5.2-GGUF 4 months ago

Error loading in ik_llama.cpp

1

#1 opened 4 months ago by

Jon-Nielsen

New activity in unsloth/GLM-5.2-GGUF 4 months ago

Is it possible to make less than 1 bit quantization?

👍🤗 2

13

#1 opened 4 months ago by

RealBar

New activity in DevQuasar/CohereLabs.command-a-reasoning-08-2025-GGUF 4 months ago

Is this working on your fork?

1

#1 opened 4 months ago by

gghfez

New activity in DevQuasar/mistralai.Mistral-Medium-3.5-128B-GGUF 5 months ago

Consider updating your GGUFs

🤝 1

2

#1 opened 5 months ago by

juliendenize

New activity in DevQuasar/MiniMaxAI.MiniMax-M2.7-GGUF 6 months ago

tiny typo in model card regarding their sizes. 2-bit Q2_K 83.3 GB 3-bit Q3_K_M 62.9 GB

1

#1 opened 6 months ago by

MartinPatterson

New activity in DevQuasar/QuixiAI.WizardLM-13B-Uncensored-GGUF 6 months ago

what version of llama architecture does this model use?

1

#1 opened 6 months ago by

saiu321

New activity in DevQuasar/sarvamai.sarvam-30b-GGUF 7 months ago

Error with llamacpp

1

#1 opened 7 months ago by

mbhagya

New activity in DevQuasar/Nanbeige.Nanbeige4.1-3B-GGUF 7 months ago

Not working in latest llama cpp versions

2

#1 opened 8 months ago by

urtuuuu

New activity in moonshotai/Kimi-K2-Thinking 8 months ago

Python script to decompress tensors?

➕🔥 4

15

#2 opened 11 months ago by

ubergarm

New activity in ubergarm/Kimi-K2.5-GGUF 8 months ago

Appreciation for IQ1_KT

🔥 1

7

#5 opened 8 months ago by

Radamanthys11

New activity in DevQuasar/Qwen.Qwen3-VL-Embedding-2B-GGUF 8 months ago

Image embedding possible via Llama.cpp ??

1

#2 opened 8 months ago by

andykensin

New activity in DevQuasar/llm_router_dataset-synth 9 months ago

generation

1

#1 opened 9 months ago by

seymanurkorkmaaz

New activity in NousResearch/k2-merged-3.5T-bf16 10 months ago

Any eval results?

#2 opened 10 months ago by

csabakecskemeti