freegheist

freegheist's activity

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

New activity in zai-org/GLM-4.7-Flash about 2 months ago

Enormous KV-cache size?

👍➕ 6

23

#3 opened about 2 months ago by

nephepritou

New activity in mistralai/Devstral-Small-2-24B-Instruct-2512 3 months ago

FP16 Weights

4

#19 opened 3 months ago by

orendar

New activity in QuantTrio/GLM-4.7-AWQ 3 months ago

Int8 Mix

#1 opened 3 months ago by

freegheist

New activity in QuantTrio/Qwen3-235B-A22B-GPTQ-Int8 5 months ago

2507 version

2

#1 opened 5 months ago by

freegheist

New activity in QuantTrio/GLM-4.6-GPTQ-Int4-Int8Mix 5 months ago

Quant Size

8

#2 opened 6 months ago by

ortegaalfredo

New activity in alpindale/GLM-4.6-INT8 5 months ago

gibberish output

2

#1 opened 5 months ago by

freegheist

New activity in unsloth/GLM-4.6-GGUF 5 months ago

Multiple chat template fixes

🚀❤️ 7

14

#2 opened 6 months ago by

danielhanchen

New activity in unsloth/GLM-4.5-GGUF 6 months ago

Corrected jinja template with tool Support works with PR llama.cpp/pull/15186

2

#5 opened 7 months ago by

xbruce22

New activity in unsloth/Qwen3-Coder-480B-A35B-Instruct-GGUF 6 months ago

UD-Q4_K_XL matches bf16 with 60.9% vs 61.8% on Aider Polyglot benchmark

🔥👍 9

3

#8 opened 8 months ago by

Fernanda24

New activity in Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-AutoRound 7 months ago

Error loading in vLLm 10.1+

👍 1

2

#2 opened 7 months ago by

freegheist

New activity in JunHowie/Qwen3-4B-Thinking-2507-GPTQ-Int8 7 months ago

Larger versions

2

#1 opened 7 months ago by

freegheist

New activity in QuantTrio/Qwen3-235B-A22B-Thinking-2507-GPTQ-Int4-Int8Mix 7 months ago

Upgrade to 1m context

5

#4 opened 7 months ago by

freegheist

New activity in QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix 7 months ago

Does it possible to create a version without MTP layer to save some VRAM

1

#1 opened 8 months ago by

adonishong

New activity in justinjja/Qwen3-235B-A22B-INT4-W4A16 11 months ago

INT 8

#2 opened 11 months ago by

freegheist

New activity in deepcogito/cogito-v1-preview-llama-70B 11 months ago

<think> in generation output

3

#2 opened 11 months ago by

wvangils

New activity in CohereLabs/c4ai-command-a-03-2025 12 months ago

Tell me how do you feel about this model without telling me how do you feel about this model

4

#5 opened about 1 year ago by

MrDevolver

Question About VRAM Requirements for Full 256K Context Length

2

#7 opened about 1 year ago by

mullerse

New activity in mistralai/Mistral-Large-Instruct-2411 over 1 year ago

can you provide the metrics

1

#5 opened over 1 year ago by

6cf

New activity in mattshumer/Reflection-Llama-3.1-70B over 1 year ago

BF16 weights?

👍 7

5

#1 opened over 1 year ago by

mpasila

New activity in open-llm-leaderboard/open_llm_leaderboard over 1 year ago

WizardLM-8x22B Evaluation failed

👍➕ 28

25

#823 opened over 1 year ago by

llama-anon