Qwen3.8-27B-opencode-adapted-bf16 is a standalone BF16 checkpoint created by merging the harness-hub/Qwen3.8-27B-opencode-adapted LoRA adapter into
Qwen/Qwen3.8-27B, enabling deployment on any inference engine without LoRA support. The adapter (r = 32, alpha = 64, targeting the q, k, v, o, gate, up, and down projections) was trained with AsyncGRPO reinforcement learning in Harbor/OpenEnv environments to serve as the backbone for the OpenCode coding agent on software-engineering and terminal tasks, with thinking mode turned off as in training. The merge applies the standardW + (alpha/r)·B@Aupdate per tensor in fp32 before casting back to BF16, preserving the base shard layout, tensor names, and all MTP tensors. According to the adapter's model card, under OpenCode it raises SWE-bench Pro (hard 51) from 35.3% to 51.0% and Terminal-Bench 2.1 from 46.4% to 52.4%, while requiring a quarter to half as many turns and generating 6–8× fewer tokens per task. These figures were measured using the adapter on the BF16 base model and have not been re-evaluated on this merged checkpoint.
[!NOTE] MTP — Speculative Decoding: Yes
[!NOTE] Multi-Token Prediction (MTP) GGUF is a specialized GGUF model file format extension that integrates speculative decoding directly into the model weights to significantly accelerate local inference. Unlike traditional speculative decoding which requires a separate, smaller "draft" model, MTP GGUF files include additional output heads within the main model architecture that predict multiple future tokens in a single forward pass.
| File Name | Quant Type | File Size | File Link | Description |
|---|---|---|---|---|
| Qwen3.8-27B-opencode-adapted.Q4_K_M.gguf | Q4_K_M | 17 GB | Link | Good quality, default size for most use cases, recommended. |
| Qwen3.8-27B-opencode-adapted.Q4_K_S.gguf | Q4_K_S | 15.8 GB | Link | Slightly lower quality with more space savings, recommended. |
| Qwen3.8-27B-opencode-adapted.Q5_K_M.gguf | Q5_K_M | 19.6 GB | Link | High quality, recommended. |
| Qwen3.8-27B-opencode-adapted.Q5_K_S.gguf | Q5_K_S | 19 GB | Link | High quality with slight space savings, recommended. |
| Qwen3.8-27B-opencode-adapted.Q8_0.gguf | Q8_0 | 29 GB | Link | Extremely high quality, generally unneeded but max available standard quant. |
| Qwen3.8-27B-opencode-adapted.mmproj-bf16.gguf | mmproj-bf16 | 931 MB | Link | Multimodal projection file in BF16 format. Used for vision/image capabilities. |
LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp
Quantized using llama.cpp by prithivMLmods.
harness-hub/Qwen3.8-27B-opencode-adapted