You can deploy this model and start earning money today!

bingleai/
FableOpus-9B-Delta-GGUF

Source: interpolators/FableOpus-9B-Delta
Family: Qwen3.5 9B
Merge method: delta_linear
Merge recipe: Fable 0.38, Opus 0.42, Opus v2 0.20
GGUF tooling: latest ggml-org/llama.cpp built in Modal
Intermediate: bf16 GGUF, deleted after quantization

Name: FableOpus-9B-Delta-GGUF
Availability: InStock

Views

No views yet

FableOpus-9B-Delta GGUF

This repo includes the requested llama.cpp quantizations in one place:

FableOpus-9B-Delta-Q2_K.gguf (3.56 GiB)
FableOpus-9B-Delta-Q3_K_M.gguf (4.31 GiB)
FableOpus-9B-Delta-Q4_K_M.gguf (5.24 GiB)
FableOpus-9B-Delta-Q6_K.gguf (6.85 GiB)
FableOpus-9B-Delta-Q8_0.gguf (8.87 GiB)

llama-cli -m FableOpus-9B-Delta-Q4_K_M.gguf -p "Write a concise plan for evaluating this model."

Use Q4_K_M as a practical default, Q6_K or Q8_0 for higher quality, and Q2_K / Q3_K_M when size matters most.