Hans-Christian Heine

chrisoutwright's activity

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

New activity in prism-ml/Ternary-Bonsai-8B-gguf 2 days ago

Q2_0 g64 ternary is ~5× slower than Q4_K_M on Samsung S22 CPU - missing optimized kernel?

1

#6 opened 2 days ago by

chrisoutwright

New activity in unsloth/gemma-4-E4B-it-qat-GGUF about 1 month ago

Can the Gemma 4 E4B vision mmproj be quantized to Q8_0 to reduce VRAM usage?

1

#7 opened about 1 month ago by

chrisoutwright

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 1 month ago

Dual RTX3090 and 64GB DDR4 + 78GB Swap. Speed: ~1.78 TPS

🤝👍 4

15

#8 opened about 2 months ago by

robert1968

New activity in unsloth/DeepSeek-V4-Flash-GGUF 2 months ago

DeepSeek-V4-Flash is now ready to run locally! 🐳

❤️👍 8

19

#6 opened 2 months ago by

danielhanchen

New activity in unsloth/gemma-4-31B-it-qat-GGUF 3 months ago

Gemma-4 QAT Special Unsloth quants

🔥 11

6

#1 opened 3 months ago by

danielhanchen

New activity in unsloth/Qwen3.5-397B-A17B-MTP-GGUF 4 months ago

1.40 to .48 token

➕ 1

2

#2 opened 4 months ago by

BrokeAmerican

UD-IQ3_S < UD-IQ3_XXS ?

1

#1 opened 4 months ago by

chrisoutwright

New activity in Tesslate/OmniCoder-9B-GGUF 5 months ago

VS Code Copilot Chat: No Response Returned When Executing Commands

#5 opened 5 months ago by

chrisoutwright

New activity in unsloth/Qwen3-Coder-Next-GGUF 6 months ago

Agent Response missing at the end in prompt/chat template? Looping end.

1

#26 opened 6 months ago by

chrisoutwright

New activity in unsloth/Apertus-70B-Instruct-2509-GGUF 7 months ago

Repetition galore ... The simple answer: Without being overly specific, the simple answer

#2 opened 7 months ago by

chrisoutwright

New activity in Daemontatox/FerrisMind 7 months ago

Recommendationconfiguration for quantizing to AWQ ? Seems hard.

#2 opened 7 months ago by

chrisoutwright

New activity in Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice 7 months ago

Low generation speed and low GPU utilization (~12%) during inference

😔👀 2

7

#18 opened 8 months ago by

Geximus

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF 8 months ago

New Chat Template + Tool Calling Fixes as of 05 Aug, 2025

👀❤️ 23

49

#10 opened about 1 year ago by

shimmyshimmer

New activity in mradermacher/Qwen3-Coder-53B-A3B-Instruct-TOTAL-RECALL-v2-MASTER-CODER-L-i1-GGUF 10 months ago

Repetition Loops

3

#1 opened 11 months ago by

chrisoutwright

New activity in unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF 12 months ago

IQ4_NL 17.3 GB and OLLAMA_KV_CACHE_TYPE' -Value 'q8_0' Gibber after certain 100k context

#16 opened 12 months ago by

chrisoutwright

New activity in mradermacher/HydraCoder-GGUF 12 months ago

HydraCoder hallucinated by pretending to give Rust code

#1 opened 12 months ago by

chrisoutwright

New activity in Daemontatox/OR1-Behemoth 12 months ago

Daemontatox/OR1-Behemoth model keep repeating the same broken Rust code

2

#1 opened 12 months ago by

chrisoutwright

New activity in nizarmichaud/whisper-large-v3-turbo-swissgerman over 1 year ago

How to use - transcriptions seems hit and miss too often?

4

#2 opened over 1 year ago by

chrisoutwright

How to use - transcriptions seems hit and miss too often?

4

#2 opened over 1 year ago by

chrisoutwright

How to use - transcriptions seems hit and miss too often?

4

#2 opened over 1 year ago by

chrisoutwright