Downloads · 30 days
123
17% of all-time downloads
Qwen3.8-27B-NVFP4-IRIS-Cache-ObjectScript
blkpws/Qwen3.8-27B-NVFP4-IRIS-Cache-ObjectScript
Qwen3.8-27B-NVFP4-IRIS-Cache-ObjectScript is a text generation model from blkpws. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
Fine-tuned Qwen3.8-27B as an InterSystems IRIS / Caché ObjectScript specialist, trained on a task-solving dataset (44% code task→solution, 16% real bugfix pairs, 31% short Q&A, 9% general anti-forgetting) with LR 1e-4…
All-time downloads
728
Public
Parameters
19.4B
42.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22 GB · 100%
Parameter types
How the weights are stored.
U817.1B · 64%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B-NVFP4-IRIS-Cache-ObjectScript
Fine-tuned Qwen3.8-27B as an InterSystems IRIS / Caché ObjectScript specialist, trained on a task-solving dataset (44% code task→solution, 16% real bugfix pairs, 31% short Q&A, 9% general anti-forgetting) with LR 1e-4 + grad-accum 2 (1200 steps, eval loss 0.966 → 0.787 monotonic), merged to BF16, then re-quantized to NVFP4 (attn FP8 dynamic, MLP NVFP4) with domain-matched ObjectScript calibration.
Won an A/B against the previous v2 fine-tune on real ObjectScript coding prompts (complete working code vs truncated prose).
Model facts
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3.8-27B (hybrid: 48 linear_attn + 16 self_attn layers) |
| Parameters (BF16) | ~27.8B (the HF "18b" label below is the quantized file size in GB, not the parameter count) |
| Default context window | 262,144 tokens (256K) — max_position_embeddings: 262144 |
| Architecture | Qwen3_5ForCausalLM, hidden 5120, 64 layers, 24 heads / 4 KV, vocab 248,320 |
| Quantization | compressed-tensors: NVFP4 (W4A4 static, group 16) on MLP + lm_head, FP8 (W8A8 static) on attention |
| Quantized size on disk | ~18-20 GB (4-bit) |
Why it shows "~18B" on Hub: HuggingFace derives the number from the safetensors storage size (~18-20 GB after 4-bit NVFP4 quantization) and displays it as "b". The model is genuinely a 27B-class model (Qwen3.8-27B, ~27.8B BF16 params); 4-bit quantization shrinks the file size, not the parameter count.
Deployment
Serve with vLLM (--quantization compressed-tensors, --max-model-len 262144).
Served model name: qwen3.8-27b-iris. Context: 262144 (256K).
On a DGX Spark (GB10/SM121), keep --gpu-memory-utilization <= 0.85 and the freeze
guards (--max-cudagraph-capture-size 4, --no-enable-flashinfer-autotune).
Generated with
- llmcompressor 0.13.0 (NVFP4 + FP8 mixed)
- Custom peft + transformers Trainer (BF16 base + 4-bit qLoRA)
Dialect
Trains on InterSystems IRIS / Caché ObjectScript (.cls / .mac / .inc).
- Task
- Text Generation
- Type
- qwen3_5_text
- License
- apache-2.0
- Languages
- en
- Created
- Aug 20, 2026
- Updated
- Aug 22, 2026