Search: github.com/Anuar81 | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: Evolved x86 AVX-512 kernels for NF4 LLM inference

github.com/Anuar81

4 months ago

2 points

2.

Show HN: Run Qwen3-Next-80B on 8GB GPU at 1tok/2s throughput

github.com/Mega4alik

9 months ago

123 points

3.

Show HN: Run gpt-oss-20b on 8GB GPUs

github.com/Mega4alik

10 months ago

6 points

4.

Show HN: oLLM – LLM Inference for large-context tasks on consumer GPUs

github.com/Mega4alik

10 months ago

3 points

5.

Show HN: Fine-tune Llama3-8B on 8GB GPU without quantization

github.com/Mega4alik

8 months ago

3 points