GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
RikiyaT
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
RikiyaT
Model Tree
Qwen/Qwen3.5-0.8B
Input Modalities
Output Modalities
Supported Functionality
From the post (thinking on, up to 32,768 tokens, several samples per problem):
| Qwen3.5-0.8B | MATH-500 (%) | GSM8K (%) | IFEval (%) | Hit token limit (%) |
|---|---|---|---|---|
| Base | 7.9 | 13.8 | 21.0 | 93.0 |
| Edited (this model) | 48.1 | 67.1 | 62.3 | 33.1 |
Independent re-run of this checkpoint: full MATH-500, 500 problems × 4 samples = 2,000 generations
(43.4M generated tokens, 51 min on an H200), with the post's protocol: vLLM, thinking on, temperature 0.6,
top_p 0.95, top_k 20, presence_penalty 1.5, max 32,768 new tokens, seed 0, last \boxed{} graded with
math-verify 0.9.0. The edited model scored 51.0%, with 31.6% of answers hitting the token limit.
A 25-problem smoke test of the base model gave 5.0%, with 95% hitting the limit.
Raw scores, per-problem results and sample generations:
eval/.
Astra's edit is published as a bit-exact diff in
RikiyaT/lm_understand-logs (exp8_math/runs/p50c/edit/).
This checkpoint was rebuilt with exp8_math/code/apply_edit.py, which sha256-verifies every rebuilt
tensor against the checkpoint evaluated in the post. Only these two tensors differ from
Qwen/Qwen3.5-0.8B @ 2fc06364715b967f1860aea9cf38778875588b17:
| Tensor | sha256 of the raw bfloat16 bytes |
|---|---|
model.language_model.layers.15.mlp.down_proj.weight | 82e2d733ea64feaeb4af93a1e065641d3df98b494a8b7576ef2f52e90fe2ee53 |
model.language_model.layers.19.mlp.down_proj.weight | 8ef3c61bc36af113ad58e89dbb0a4a14dcba5a45cb750c15ab515c82ddd12eb2 |
This checkpoint and the re-run above were built by akhaliq with
ML Intern on Hugging Face Jobs, 2026-11-02: the edit was rebuilt and
hash-verified on CPU, and the benchmark run on an NVIDIA H200 with vLLM 0.33.0 / transformers 5.20.2 /
math-verify 0.9.0, following exp8_math/code/evaluate.py (thinking on, think35 sampling,
last-\boxed{} grading). One substitution: the post evaluated a text-only export of the model, and this
checkpoint is the full multimodal release. The language-model tensors are identical (hash-verified), and
text prompts do not use the vision tower.
python
from vllm import LLM, SamplingParamsfrom transformers import AutoTokenizer ckpt = "RikiyaT/Qwen3.5-0.8B-weight-space-programming"tok = AutoTokenizer.from_pretrained(ckpt)llm = LLM(model=ckpt, dtype="bfloat16", max_model_len=34816) prompt = tok.apply_chat_template( [{"role": "user", "content": "What is $2^{10} + 24$?\nPlease reason step by step, and put your final answer within \\boxed{}."}], tokenize=False, add_generation_prompt=True, enable_thinking=True)sp = SamplingParams(n=1, temperature=0.6, top_p=0.95, top_k=20, presence_penalty=1.5, max_tokens=32768, seed=0)print(llm.generate([prompt], sp)[0].outputs[0].text)exp8_math/, CC BY 4.0 / MIT)eval/): MATH-500 (HuggingFaceH4/MATH-500), math-verify 0.9.0from vllm import LLM, SamplingParamsfrom transformers import AutoTokenizer ckpt = "RikiyaT/Qwen3.5-0.8B-weight-space-programming"tok = AutoTokenizer.from_pretrained(ckpt)llm = LLM(model=ckpt, dtype="bfloat16", max_model_len=34816) prompt = tok.apply_chat_template( [{"role": "user", "content": "What is $2^{10} + 24$?\nPlease reason step by step, and put your final answer within \\boxed{}."}], tokenize=False, add_generation_prompt=True, enable_thinking=True)sp = SamplingParams(n=1, temperature=0.6, top_p=0.95, top_k=20, presence_penalty=1.5, max_tokens=32768, seed=0)print(llm.generate([prompt], sp)[0].outputs[0].text)