41 6 84

Chris Scott

chriswritescode

https://chriswritescode.dev

chriswritescode-dev

AI & ML interests

None yet

Recent Activity

liked a model about 3 hours ago

Qwen/Qwen3.5-397B-A17B

reacted to danielhanchen's post with 🔥 about 20 hours ago

You can now run MiniMax-2.5 locally! 🚀 At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat. Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s. Guide: https://unsloth.ai/docs/models/minimax-2.5 GGUF: https://huggingface.co/unsloth/MiniMax-M2.5-GGUF

liked a model 1 day ago

MiniMaxAI/MiniMax-M2.5

View all activity

Organizations

None yet

New activity in QuantTrio/GLM-4.7-GPTQ-Int4-Int8Mix about 1 month ago

Accessing LLM, response without<think>start tag

#2 opened about 2 months ago by

sudage

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

best coding&reasoning model. thank you Z.AI

👍 6

#10 opened about 2 months ago by

Tugay31

New activity in baseten-admin/glm-4.7-fp4 about 2 months ago

did you use the default nemotron dataset ?

#1 opened about 2 months ago by

chriswritescode

New activity in XiaomiMiMo/MiMo-V2-Flash about 2 months ago

Great Model! - sglang mtp support for triton backend

👍 3

#19 opened about 2 months ago by

chriswritescode

New activity in zai-org/GLM-4.6V 2 months ago

vLLM load error

👍 3

#2 opened 2 months ago by

srinivasbilla

New activity in cerebras/GLM-4.6-REAP-268B-A32B-FP8 3 months ago

Thank you!!

🤗 🤝 2

#1 opened 4 months ago by

rascazzione

New activity in QuantTrio/GLM-4.6-GPTQ-Int4-Int8Mix 4 months ago

Appreciation

❤️ 1

#3 opened 4 months ago by

chriswritescode

Quant Size

#2 opened 5 months ago by

ortegaalfredo

New activity in QuantTrio/GLM-4.6-AWQ 5 months ago

Thank you!!!

#1 opened 5 months ago by

chriswritescode

New activity in QuantTrio/GLM-4.5-AWQ 5 months ago

NVfp4 request with 16bit activations

#5 opened 5 months ago by

chriswritescode

New activity in QuantTrio/GLM-4.5V-AWQ 5 months ago

model is not performing as good as GLM-4.5-Air-AWQ-FP16Mix

#1 opened 6 months ago by

hareram241

New activity in openai/gpt-oss-120b 6 months ago

Request: 4-bit GPTQ or AWQ quantized version of openai/gpt-oss-20b

🚀 ❤️ 17

#32 opened 6 months ago by

powtac

New activity in openai/gpt-oss-120b 7 months ago

VLLM - Flash-attn 3

#23 opened 7 months ago by

chriswritescode

New activity in cyankiwi/GLM-4.5-Air-AWQ-4bit 7 months ago

Please make one for the larger Non Air Variant

#2 opened 7 months ago by

chriswritescode

New activity in zai-org/GLM-4.5 7 months ago

AWQ 4Bit / GPTQ with full precision gates and head? Please

#4 opened 7 months ago by

chriswritescode

New activity in chriswritescode/Qwen3-235B-A22B-Instruct-2507-AWQ-Swift 7 months ago

Qwen3-235B-A22B-Instruct-2507, int4-w4a16 or awq? Which one has better accuracy recovery?

#1 opened 7 months ago by

traphix

New activity in chriswritescode/Qwen3-235B-A22B-Instruct-2507-INT4-W4A16 7 months ago

Type of quantization

#1 opened 7 months ago by

systemicAnomaly

New activity in koushd/Qwen3-235B-A22B-Instruct-2507-AWQ 7 months ago

Quantization Config

#2 opened 7 months ago by

chriswritescode

New activity in NVFP4/Qwen3-235B-A22B-Instruct-2507-FP4 7 months ago

quantization method?

#2 opened 7 months ago by

chriswritescode

New activity in LGAI-EXAONE/EXAONE-4.0-32B-FP8 7 months ago

VLLM

#1 opened 7 months ago by

chriswritescode

Chris Scott

AI & ML interests

Recent Activity

Organizations

chriswritescode's activity

Accessing LLM, response without<think>start tag

best coding&reasoning model. thank you Z.AI

did you use the default nemotron dataset ?

Great Model! - sglang mtp support for triton backend

vLLM load error

Thank you!!

Appreciation

Quant Size

Thank you!!!

NVfp4 request with 16bit activations

model is not performing as good as GLM-4.5-Air-AWQ-FP16Mix

Request: 4-bit GPTQ or AWQ quantized version of openai/gpt-oss-20b

VLLM - Flash-attn 3

Please make one for the larger Non Air Variant

AWQ 4Bit / GPTQ with full precision gates and head? Please

Qwen3-235B-A22B-Instruct-2507, int4-w4a16 or awq? Which one has better accuracy recovery?

Type of quantization

Quantization Config

quantization method?

VLLM