Text Generation
MLX
Safetensors
GGUF
Rust
qwen3_5_text
4b
agentic-coding
android
apple-silicon
attested
bash
c
chain-of-custody
chinese
code
code-completion
code-generation
code-infill
coder
coding
consumer-gpu
cpp
cryptographically-verified
css
delta-forge
edge-inference
embedded
english
forge-alloy
function-calling
ggml
go
html
iphone
java
javascript
kotlin
llama-cpp
lm-studio
local-inference
macbook
mobile
multilingual
ollama
on-device
php
programming
python
q4-k-m
quantized
qwen
qwen3
qwen3.5
raspberry-pi
reproducible
ruby
software-engineering
sql
swift
typescript
Instructions to use continuum-ai/qwen3.5-4b-code-forged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use continuum-ai/qwen3.5-4b-code-forged with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("continuum-ai/qwen3.5-4b-code-forged") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use continuum-ai/qwen3.5-4b-code-forged with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "continuum-ai/qwen3.5-4b-code-forged" --prompt "Once upon a time"
- Atomic Chat
Commit History
-
fix: use hf.co (CORS-open) in verify URLs
Verified signature8875519 -
fix: verify URL uses source@hash for direct fetch
Verified signature7a81f9b
-
Regenerate QR for new verify URL (435ff486e11ed54d)
Verified signaturead43b93 -
Regenerate model card from corrected alloy (alloyHash 435ff486e11ed54d)
Verified signature5b41180 -
Correct qwen3.5-4b-code-forged.alloy.json pass@1 to canonical evalplus convention (v1.0.0)
Verified signature992add5
-
card: footer v3 — OLMoE shipped + §4.1.3.4.1 discipline gate
Verified signature4c75450 -
card: refresh footer with comprehensive forge queue (10 architectures)
Verified signature6669aff -
card: refresh with methodology note + org front-door footer
Verified signaturee8ed20d
-
Upload README.md with huggingface_hub
Verified signatureedb9f1e -
wrong QR code
Verified signature7af909d -
Upload alloy-qr.png with huggingface_hub
Verified signatureaf4a30f -
Upload alloy-qr.png with huggingface_hub
Verified signature70fb34b -
Upload README.md with huggingface_hub
Verified signature165f1ae -
Upload README.md with huggingface_hub
Verified signature3042df4 -
Upload qwen3.5-4b-code-forged.alloy.json with huggingface_hub
Verified signature6cdb8df -
Upload README.md with huggingface_hub
Verified signature078e83b -
Upload alloy-qr.png with huggingface_hub
Verified signature3a129e6 -
Upload tokenizer.json with huggingface_hub
Verified signature253e71a -
Upload model.safetensors with huggingface_hub
Verified signature983cac8 -
Upload qwen3.5-4b-code-test.alloy.json with huggingface_hub
Verified signaturede4868d -
Upload qwen3.5-4b-code-forged.alloy.json with huggingface_hub
Verified signature5ec9d1e -
Upload benchmark/refactoring.txt with huggingface_hub
Verified signature3c06329 -
Upload benchmark/debugging.txt with huggingface_hub
Verified signature5e72a4c -
Upload benchmark/concurrent_system.txt with huggingface_hub
Verified signaturebc345bf -
Upload benchmark/system_design.txt with huggingface_hub
Verified signaturefebe2a8 -
Upload forging_results.json with huggingface_hub
Verified signaturedeaa68a -
Upload README.md with huggingface_hub
Verified signature0534d08
-
Add Qwen2.5-Coder-1.5B benchmark comparison — forged model beats purpose-built coder
Verified signatureab22f51 -
Add GGUF Q4_K_M benchmark results (HumanEval 53.0%, HumanEval+ 47.0%)
Verified signaturef5f576d -
Add HumanEval benchmark results (57.3% pass@1)
Verified signature44c62d8
-
Upload README.md with huggingface_hub
Verified signature73d687b -
Upload README.md with huggingface_hub
Verified signature0f6549a -
Upload README.md with huggingface_hub
Verified signature2eeb77d -
Upload config.json with huggingface_hub
Verified signature590e7ee -
Upload model.safetensors with huggingface_hub
Verified signature80206c0 -
Upload benchmark/refactoring.txt with huggingface_hub
Verified signature0f68660 -
Upload benchmark/debugging.txt with huggingface_hub
Verified signature736f913 -
Upload benchmark/concurrent_system.txt with huggingface_hub
Verified signature0f99ac6 -
Upload benchmark/system_design.txt with huggingface_hub
Verified signature50ef9bf -
Upload forging_results.json with huggingface_hub
Verified signature5179a82 -
Upload README.md with huggingface_hub
Verified signature7c6cf2c -
Upload config.json with huggingface_hub
Verified signature4709049
-
Upload generation_config.json with huggingface_hub
Verified signature9aa74b6 -
Upload tokenizer_config.json with huggingface_hub
Verified signatureae64aa6 -
Upload tokenizer.json with huggingface_hub
Verified signature9b12632 -
Upload config.json with huggingface_hub
Verified signaturee0fcde0 -
Upload model.safetensors with huggingface_hub
Verified signature3fed94c -
Upload benchmark/refactoring.txt with huggingface_hub
Verified signaturef860039 -
Upload benchmark/debugging.txt with huggingface_hub
Verified signature1c90e12 -
Upload benchmark/concurrent_system.txt with huggingface_hub
Verified signaturec923c16