Total runs:
650.8K
Run Growth:
602.0K
Growth Rate:
94.94%
Sponsored by
APIMaster
AtomicChat / Ornith-9B-GGUF
Model's Last Updated: July 23 2026
text-generation
Introduction of Ornith-9B-GGUF
Model Details of Ornith-9B-GGUF
Ornith 1.0 9B , self-quantized to GGUF by Atomic Chat . Built straight from DeepReinforce's original weights with a per-tensor importance matrix. Runs fully offline.
Highlights
- A self-improving open-source family for agentic coding from DeepReinforce, built for tool-calling and terminal-based coding agents.
- Post-trained on top of Gemma 4 and Qwen 3.5 , the smallest, fastest member of the Ornith 1.0 lineup.
- Strong agentic coding scores for its size : 69.4 on SWE-bench Verified and 43.1 on Terminal-Bench 2.1 (Terminus-2).
-
Dense architecture, 32 layers
,
qwen3_5model type with ahidden_sizeof 4096. - 262,144-token native context for long files and multi-step agent traces.
- Pure open : MIT licensed, globally accessible with no regional limits.
-
Full quant ladder
with an importance matrix on every quant over
calibration_datav3.
These GGUFs are self-quantized from the original weights , not a repack. The importance matrix keeps low-bit quants closer to the full-precision model.
Always pass
--jinjaso the Ornith 1.0 9B chat template is applied. Without it the model can emit malformed turns.
Model Overview
| Property | Value |
|---|---|
| Base model |
deepreinforce-ai/Ornith-1.0-9B
|
| Total parameters | ~9B (model name; card states no exact figure in prose) |
| Layers | 32 |
| Context length | 262,144 |
| Architecture |
qwen3_5
dense causal LM, post-trained on Gemma 4 and Qwen 3.5
|
| This repo | GGUF quants (imatrix), full ladder from the original weights |
Scores are DeepReinforce's published results for the base
deepreinforce-ai/Ornith-1.0-9B
. These are full-precision scores; the quants here run the same model locally. Quantization preserves the large majority of this, with
Q4_K_M
and up sitting within a point or two of full precision.
Choosing a quant
| Quant | Size | Notes |
|---|---|---|
IQ4_XS
|
5.2 GB | Excellent quality for size. Recommended low-bit. |
Q4_K_M
|
5.6 GB | Recommended default. Best balance of size, speed and quality. |
UD-Q4_K_XL
|
6.4 GB | Dynamic. Token embeddings and output kept at Q8_0 for higher quality at a Q4 footprint. |
Q5_K_M
|
6.5 GB | Higher quality, low loss. |
Q6_K
|
7.4 GB | Near lossless. |
Q8_0
|
9.5 GB | Effectively lossless, reference quality. |
Pick the largest file that fits your (V)RAM with room for context.
Q4_K_MorUD-Q4_K_XLis the sweet spot for most setups;Q6_KorQ8_0for maximum fidelity.
Get started
Run Ornith 1.0 9B locally with:
-
Atomic Chat
:
the easiest path. Open the app, search
AtomicChat/ornith-9b-GGUF, pick a quant, hit Use this model . -
llama.cpp:
llama-server -hf AtomicChat/ornith-9b-GGUF:Q4_K_M --jinja -c 8192 -
Ollama:
ollama run hf.co/AtomicChat/ornith-9b-GGUF:Q4_K_M - LM Studio / Jan: search the repo id, download any quant.
Best practices
| Parameter | Value |
|---|---|
| temperature | 0.6 |
| top_p | 0.95 |
| top_k | 20 |
DeepReinforce's recommended sampling parameters. The card notes that
temperature=1.0
reproduces the reported benchmark setup.
Run in llama.cpp
git clone https://github.com/ggerganov/llama.cpp
cmake llama.cpp -B llama.cpp/build -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
cmake --build llama.cpp/build --config Release -j --target llama-cli llama-server
./llama.cpp/build/bin/llama-server \
-hf AtomicChat/ornith-9b-GGUF:UD-Q4_K_XL \
--jinja -ngl 99 -c 8192 -fa on
How these were made
-
Download
deepreinforce-ai/Ornith-1.0-9B(original weights). - Convert to f16 GGUF with llama.cpp .
-
Build an importance matrix over
calibration_datav3withllama-imatrix. -
Quantize the full ladder with
--imatrix. -
UD-Q4_K_XLadditionally pins the token-embedding and output tensors toQ8_0.
License
Released by DeepReinforce under the MIT license, globally accessible with no regional limits. Quantized by Atomic Chat.
Runs of AtomicChat Ornith-9B-GGUF on huggingface.co
914
Total runs
-4
24-hour runs
-32
3-day runs
-55
7-day runs
-407
30-day runs
More Information About Ornith-9B-GGUF huggingface.co Model
Url of Ornith-9B-GGUF
Ornith-9B-GGUF huggingface.co Url
Provider of Ornith-9B-GGUF huggingface.co
Other API from AtomicChat
Updated:August 27 2026
Total runs:
274.3K
Run Growth:
11.7K
Growth Rate:
4.21%
Total runs:
65.7K
Run Growth:
4.0K
Growth Rate:
6.08%
Total runs:
64.9K
Run Growth:
3.4K
Growth Rate:
5.18%
Total runs:
64.8K
Run Growth:
2.9K
Growth Rate:
4.34%
Total runs:
46.2K
Run Growth:
3.5K
Growth Rate:
7.25%
Total runs:
44.7K
Run Growth:
-243.1K
Growth Rate:
-530.80%
Total runs:
30.8K
Run Growth:
-44.6K
Growth Rate:
-140.60%
Total runs:
8.4K
Run Growth:
2.6K
Growth Rate:
32.53%
Total runs:
6.3K
Run Growth:
-2.4K
Growth Rate:
-39.14%
Total runs:
5.8K
Run Growth:
1.4K
Growth Rate:
24.17%
Total runs:
5.7K
Run Growth:
4.2K
Growth Rate:
74.92%
Total runs:
5.6K
Run Growth:
1.7K
Growth Rate:
34.31%
Total runs:
5.5K
Run Growth:
-4.7K
Growth Rate:
-86.88%
Total runs:
4.3K
Run Growth:
2.5K
Growth Rate:
59.60%
Total runs:
4.0K
Run Growth:
-1.9K
Growth Rate:
-50.21%
Total runs:
3.1K
Run Growth:
1.3K
Growth Rate:
46.45%
Total runs:
3.0K
Run Growth:
3.0K
Growth Rate:
100.00%
Total runs:
2.8K
Run Growth:
1.7K
Growth Rate:
61.20%
Total runs:
2.7K
Run Growth:
687
Growth Rate:
24.35%
Total runs:
2.6K
Run Growth:
-288
Growth Rate:
-10.66%
Total runs:
2.3K
Run Growth:
-1.7K
Growth Rate:
-74.89%
Total runs:
2.1K
Run Growth:
-7.9K
Growth Rate:
-385.97%
Total runs:
1.9K
Run Growth:
-3.3K
Growth Rate:
-175.77%
Total runs:
1.9K
Run Growth:
335
Growth Rate:
17.85%
Total runs:
1.8K
Run Growth:
-8.2K
Growth Rate:
-451.10%
Total runs:
1.7K
Run Growth:
657
Growth Rate:
37.65%
Total runs:
1.6K
Run Growth:
440
Growth Rate:
26.88%
Total runs:
1.6K
Run Growth:
1.6K
Growth Rate:
100.00%
Total runs:
1.5K
Run Growth:
-5.9K
Growth Rate:
-399.66%
Total runs:
1.5K
Run Growth:
634
Growth Rate:
43.22%
Total runs:
1.4K
Run Growth:
-11.7K
Growth Rate:
-776.62%
Total runs:
1.2K
Run Growth:
1.2K
Growth Rate:
100.00%
Total runs:
1.0K
Run Growth:
501
Growth Rate:
47.44%
Total runs:
1.0K
Run Growth:
1.0K
Growth Rate:
100.00%
Total runs:
986
Run Growth:
-341
Growth Rate:
-32.69%
Total runs:
903
Run Growth:
285
Growth Rate:
32.09%
Total runs:
839
Run Growth:
834
Growth Rate:
100.00%
Total runs:
833
Run Growth:
251
Growth Rate:
32.72%
Total runs:
826
Run Growth:
441
Growth Rate:
53.39%
Total runs:
807
Run Growth:
608
Growth Rate:
75.15%
Total runs:
722
Run Growth:
686
Growth Rate:
100.00%
Total runs:
706
Run Growth:
234
Growth Rate:
33.82%
Total runs:
672
Run Growth:
-3.2K
Growth Rate:
-474.93%
Total runs:
602
Run Growth:
602
Growth Rate:
100.00%
Total runs:
564
Run Growth:
-62
Growth Rate:
-11.13%
Total runs:
498
Run Growth:
12
Growth Rate:
2.44%
Total runs:
486
Run Growth:
-119
Growth Rate:
-23.15%
Total runs:
465
Run Growth:
108
Growth Rate:
23.18%
Total runs:
429
Run Growth:
-426
Growth Rate:
-99.30%
Total runs:
372
Run Growth:
47
Growth Rate:
12.30%
Total runs:
360
Run Growth:
-387
Growth Rate:
-106.03%
Total runs:
359
Run Growth:
-95
Growth Rate:
-26.84%
Total runs:
353
Run Growth:
-47
Growth Rate:
-11.78%
Total runs:
352
Run Growth:
334
Growth Rate:
83.71%
Total runs:
350
Run Growth:
-258
Growth Rate:
-71.27%
Total runs:
272
Run Growth:
-109
Growth Rate:
-37.98%
Total runs:
262
Run Growth:
-18
Growth Rate:
-6.87%
Total runs:
250
Run Growth:
107
Growth Rate:
41.96%
Total runs:
247
Run Growth:
19
Growth Rate:
7.36%
Total runs:
245
Run Growth:
-84
Growth Rate:
-32.31%
Total runs:
242
Run Growth:
52
Growth Rate:
21.85%
Total runs:
203
Run Growth:
-147
Growth Rate:
-72.41%
Total runs:
201
Run Growth:
45
Growth Rate:
22.50%
Total runs:
183
Run Growth:
-157
Growth Rate:
-84.41%
Total runs:
171
Run Growth:
-117
Growth Rate:
-69.23%
Total runs:
168
Run Growth:
-980
Growth Rate:
-573.10%
Total runs:
166
Run Growth:
-1.8K
Growth Rate:
-1073.17%
Total runs:
166
Run Growth:
-5
Growth Rate:
-2.99%
Total runs:
144
Run Growth:
-17
Growth Rate:
-11.41%
Total runs:
140
Run Growth:
-58
Growth Rate:
-40.85%
Total runs:
131
Run Growth:
-85
Growth Rate:
-63.91%
Total runs:
131
Run Growth:
23
Growth Rate:
17.29%
Total runs:
119
Run Growth:
-167
Growth Rate:
-141.53%
Total runs:
117
Run Growth:
117
Growth Rate:
100.00%
Total runs:
117
Run Growth:
104
Growth Rate:
88.89%
Total runs:
116
Run Growth:
-113
Growth Rate:
-96.58%
Total runs:
113
Run Growth:
-6.7K
Growth Rate:
-5652.54%
Total runs:
109
Run Growth:
-43
Growth Rate:
-38.39%
Total runs:
107
Run Growth:
-29
Growth Rate:
-25.66%
Total runs:
99
Run Growth:
-35
Growth Rate:
-34.65%
Total runs:
98
Run Growth:
-102
Growth Rate:
-106.25%
Total runs:
94
Run Growth:
-183
Growth Rate:
-188.66%
Total runs:
94
Run Growth:
82
Growth Rate:
87.23%
Total runs:
92
Run Growth:
-178
Growth Rate:
-187.37%
Total runs:
87
Run Growth:
-111
Growth Rate:
-124.72%
Total runs:
84
Run Growth:
-206
Growth Rate:
-239.53%
Total runs:
82
Run Growth:
-145
Growth Rate:
-166.67%
Total runs:
78
Run Growth:
-180
Growth Rate:
-214.29%
Total runs:
77
Run Growth:
-150
Growth Rate:
-180.72%
Total runs:
73
Run Growth:
-55
Growth Rate:
-68.75%
Total runs:
67
Run Growth:
26
Growth Rate:
36.11%
Total runs:
67
Run Growth:
-67
Growth Rate:
-97.10%
Total runs:
58
Run Growth:
17
Growth Rate:
27.42%
Total runs:
57
Run Growth:
-4
Growth Rate:
-6.90%
Total runs:
53
Run Growth:
-245
Growth Rate:
-445.45%
Total runs:
47
Run Growth:
16
Growth Rate:
32.00%
Total runs:
38
Run Growth:
3
Growth Rate:
7.50%