GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
saidutta69
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
saidutta69
Model Tree
Qwen/Qwen2.5-Coder-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Full GGUF ladder included — pick the quant that fits your card:
| Your GPU | Recommended quant | Weights |
|---|---|---|
| RTX 3060 / 4070 / 5070 (12 GB) | Q8_0 | 1.65 GB |
| RTX 4060 / 3070 (8 GB) | Q6_K | 1.27 GB |
| GTX 1660 Super / 2060 / 3050 laptop (6 GB) | Q5_K_M | 1.13 GB |
| CPU-only / Apple Silicon | Q4_K_M | fits in system RAM |
Weights only, at this model's 1.5B native size; add ~1 GB for context. OOM? Drop one quant level. Headroom to spare? Go one up.
| Parameter | Value |
|---|---|
| direction_index | 18.15 |
| attn.o_proj.max_weight | 1.29 |
| attn.o_proj.max_weight_position | 16.86 |
| attn.o_proj.min_weight | 1.06 |
| attn.o_proj.min_weight_distance | 14.41 |
| mlp.down_proj.max_weight | 1.01 |
| mlp.down_proj.max_weight_position | 24.99 |
| mlp.down_proj.min_weight | 0.88 |
| Metric | This model | Original model (Qwen/Qwen2.5-Coder-1.5B-Instruct) |
|---|---|---|
| KL divergence | 0.0278 | 0 (by definition) |
| Refusals | 5/100 | 95/100 |
Made with ❤️ by RACER IS OP — follow for more uncensored models
Full quantization set (14 quants + F16) produced with llama.cpp.
| File | Format | Size |
|---|---|---|
Qwen2.5-Coder-1.5B-Instruct-heretic-F16.gguf | GGUF F16 | 3.09 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q2_K.gguf | GGUF Q2_K | 0.68 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-IQ3_S.gguf | GGUF IQ3_S | 0.76 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q3_K_S.gguf | GGUF Q3_K_S | 0.76 GB |
Loads natively in llama.cpp / Ollama / LM Studio / Jan.
Run llama serve -hf saidutta69/Qwen2.5-Coder-1.5B-Instruct-heretic to pull the default quant.
bash
# llama.cppllama serve -hf saidutta69/Qwen2.5-Coder-1.5B-Instruct-heretic
python
# transformersfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_name = "saidutta69/Qwen2.5-Coder-1.5B-Instruct-heretic"model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained(model_name)messages = [{"role": "user", "content": "Write a quick sort in Python."}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,return_dict=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang.
Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it — don't put this behind an unmoderated public-facing endpoint serving third parties. It inherits Qwen2.5-Coder-1.5B-Instruct's factual limitations and biases; abliteration removes refusal directions, it doesn't add capability or judgment.
Inherits the apache-2.0 license from the base model.
See the base model card at Qwen/Qwen2.5-Coder-1.5B-Instruct for the original architecture, training details, requirements, and citation.
| mlp.down_proj.min_weight_distance | 15.30 |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q3_K_M.gguf | GGUF Q3_K_M | 0.82 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q3_K_L.gguf | GGUF Q3_K_L | 0.88 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-IQ4_XS.gguf | GGUF IQ4_XS | 0.90 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q4_K_S.gguf | GGUF Q4_K_S | 0.94 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q4_0.gguf | GGUF Q4_0 | 0.93 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q4_1.gguf | GGUF Q4_1 | 1.02 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q4_K_M.gguf | GGUF Q4_K_M | 0.99 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q5_K_S.gguf | GGUF Q5_K_S | 1.10 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q5_K_M.gguf | GGUF Q5_K_M | 1.13 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q6_K.gguf | GGUF Q6_K | 1.27 GB |
Qwen2.5-Coder-1.5B-Instruct-heretic-Q8_0.gguf | GGUF Q8_0 | 1.65 GB |