Hugging Face's logo

Spaces:
halley-ai
/
README
No application file

App Files Community
1
sebastavar commited on
Commit
8af6c4f
·
verified ·
1 Parent(s): 3134a0f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -18,7 +18,8 @@ High-quality, Apple-Silicon–optimized **MLX** builds, tools, and evals — foc
18
  ## 🚀 Featured models
19
  | Repo | Bits/GS | Footprint | Notes |
20
  |---|---:|---:|---|
21
- | **HalleyAI/gpt-oss-20b-MLX-4bit-gs32** | Q4 / 32 | ~13.1 GB | Best speed on 32 GB; near-baseline quality (+1.81% PPL vs 8-bit) |
 
22
  | **HalleyAI/gpt-oss-20b-MLX-6bit-gs32** | Q6 / 32 | ~18.4 GB | Near-Q8 fidelity (-0.51% PPL vs 8-bit) |
23
  | **Reference (8-bit)** | Q8 / 32 | — | Use upstream: `lmstudio-community/gpt-oss-20b-MLX-8bit` |
24
 
 
18
  ## 🚀 Featured models
19
  | Repo | Bits/GS | Footprint | Notes |
20
  |---|---:|---:|---|
21
+ | **HalleyAI/gpt-oss-20b-MLX-4bit-gs32** | Q4 / 32 | ~13.1 GB | |
22
+ | **HalleyAI/gpt-oss-20b-MLX-5bit-gs32** | Q5 / 32 | ~15.8 GB | Near-Q8 fidelity (-0.51% PPL vs 8-bit) |
23
  | **HalleyAI/gpt-oss-20b-MLX-6bit-gs32** | Q6 / 32 | ~18.4 GB | Near-Q8 fidelity (-0.51% PPL vs 8-bit) |
24
  | **Reference (8-bit)** | Q8 / 32 | — | Use upstream: `lmstudio-community/gpt-oss-20b-MLX-8bit` |
25