Qwen3.8-27B-opencode-adapted GGUF

harness-hub/Qwen3.8-27B-opencode-adapted (revision b4171c0) merged into Qwen/Qwen3.8-27B (revision 3756181) and converted to GGUF for llama.cpp: ready-to-run files, no --lora needed. Every file keeps Qwen's multi-token-prediction (MTP) layer, so llama-server can use it for faster decoding, and mmproj-Qwen3.8-27B-opencode-F16.gguf adds image input.

harness-hub trained this LoRA with reinforcement learning (AsyncGRPO in TRL) to be the model behind the OpenCode coding agent on software-engineering and terminal tasks. Their published results, under OpenCode with thinking off: SWE-bench Pro (hard 51) 35.3% โ†’ 51.0% and Terminal-Bench 2.1 46.4% โ†’ 52.4% against the base model, and with thinking off it matches the base model thinking at its highest effort while generating about a sixth of the tokens. See the original adapter card for the method, data and full results.

File Size Same next token as BF16 Mean KL divergence
Qwen3.8-27B-opencode-Q6_K.gguf (recommended) 22.4 GB 98.7% 0.0197
Qwen3.8-27B-opencode-Q8_0.gguf 29.0 GB 99.5% 0.0002
Qwen3.8-27B-opencode-Q4_K_M.gguf 16.8 GB 94.2% 0.0689
mmproj-Qwen3.8-27B-opencode-F16.gguf 0.9 GB vision projector

Q6_K is the recommended balance of size and fidelity; Q8_0 is closest to the BF16 weights, Q4_K_M is the smallest. For Apple Silicon there are also MLX builds.

Use with OpenCode

The adapter was trained and evaluated with thinking off, so keep it off:

hf download netprojects/Qwen3.8-27B-opencode-adapted-GGUF Qwen3.8-27B-opencode-Q6_K.gguf mmproj-Qwen3.8-27B-opencode-F16.gguf --local-dir .

llama-server -m Qwen3.8-27B-opencode-Q6_K.gguf -mm mmproj-Qwen3.8-27B-opencode-F16.gguf \
  --jinja --chat-template-kwargs '{"enable_thinking": false}' \
  --spec-type draft-mtp -c 65536 --port 8000 --alias qwen3.8-opencode

--spec-type draft-mtp turns on the built-in MTP layer; leave it out for plain decoding, and leave out -mm if you do not need images. Then add the server to ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "local": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "http://localhost:8000/v1", "apiKey": "dummy" },
      "models": { "qwen3.8-opencode": {} }
    }
  }
}
opencode run --model local/qwen3.8-opencode "Find out why the tests in tests/test_parser.py fail and fix the bug."

Faster decoding with MTP

Measured with llama-server (Homebrew llama.cpp, commit b1b770d90) on a MacBook Pro M5 Max: greedy, thinking off, 5 prompts ร— 256 tokens from GSM8K, MATH-500, HumanEval, MBPP and MT-Bench, with other services running on the Mac, so treat the speeds as indicative.

File Plain --spec-type draft-mtp Drafts accepted
Q4_K_M 27 tok/s 53 tok/s (ร—1.97) 77%
Q6_K 22 tok/s 46 tok/s (ร—2.07) 73%
Q8_0 18 tok/s 43 tok/s (ร—2.36) 74%

With Splash

These builds also run in Splash (1.7.0), which uses its own DFlash2 draft model for speculative decoding. Measured on the same 5 prompts ร— 256 tokens, thinking off, on 19 November 2026 with other models loaded on the Mac, so treat the speeds as indicative; text, tool calling and image input passed on every build:

File Decode speed End to end, incl. prompt Tokens per cycle
Q4_K_M 144 tok/s 111 tok/s 6.6
Q6_K 129 tok/s 98 tok/s 6.9
Q8_0 105 tok/s 85 tok/s 6.6
splash serve --model-dir Qwen3.8-27B-opencode-Q6_K.gguf --mmproj mmproj-Qwen3.8-27B-opencode-F16.gguf \
  --model local/qwen3.8-opencode --reasoning-effort none

What was checked

On a MacBook Pro M5 Max (128 GB), 18 November 2026.

  • Merge. All 256 adapted modules (q, k, v, o in the 16 full-attention layers; gate, up, down in all 64 layers) equal W + 2.0 ยท B @ A rounded to bf16, checked element by element; every other tensor, including the MTP layer and the vision encoder, is byte-identical to Qwen3.8-27B.
  • Quantization. Each file was compared with the BF16 GGUF using llama-perplexity's KL-divergence mode on the chat-formatted outputs of 12 short prompts (table above).
  • llama-server (thinking off, with mmproj): on Q8_0, Q6_K and Q4_K_M a short arithmetic question was answered correctly, an agent-style prompt with bash and read tools produced a well-formed bash tool call, and a test image was described correctly (red square, blue circle).
  • Source files. Every file of both pinned upstream revisions matches the Hub's SHA-256 hashes.

Converted with llama.cpp's convert_hf_to_gguf.py at commit 8642541b2 and quantized with llama-quantize from Homebrew llama.cpp (commit b1b770d90). The tokenizer and chat template are harness-hub's files, embedded unchanged.

Credits

The adapter is by harness-hub; the base model is Qwen3.8-27B by the Qwen Team, Alibaba Cloud. If you use the model, please cite their work (see the adapter card and the Qwen3.8-27B card).

License

Apache-2.0, as Qwen3.8-27B and the harness-hub adapter. LICENSE is the Apache-2.0 text from the Qwen3.8-27B repository and NOTICE describes the conversion and credits harness-hub and the Qwen Team (Alibaba Cloud).

Published by NetProjects (Internet Projects Ltd). Not affiliated with Hugging Face, harness-hub or Alibaba.

More builds from NetProjects: huggingface.co/netprojects ยท netprojects.com

Downloads last month
-
GGUF
Model size
27B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for netprojects/Qwen3.8-27B-opencode-adapted-GGUF

Base model

Qwen/Qwen3.8-27B
Quantized
(6)
this model

Collection including netprojects/Qwen3.8-27B-opencode-adapted-GGUF