Qwen2.5 Coder 1.5B abliterated

Qwen2.5 Coder 1.5B with refusals removed (abliterated); fits any 8 GB machine. Chat in your browser, plus an OpenAI-compatible API.

Engine: llama.cpp · Q4_K_M
Size: 1.1 GB
GPU memory: 3.5 GiB or more
Runs on

Pick a machine

No machine can run this right now.

New machines appear as hosts connect them.

Have a GPU? Earn with it See all machines

Doesn't fit (3)

1× Apple M5 Max (40-core GPU) · New hostthis host has opted out of uncensored models1× Apple M3 Max (30-core GPU) · New hostthis host has opted out of uncensored models1× Apple M4 Pro (20-core GPU) · New hostthis host has opted out of uncensored models

Hardware that can run this

Nothing that can run this is online right now.

20 more devices could run it, none online

Hardware	Fits	Est. speed
RTX 3080 Ti · 12 GB	Q4_K_M, Q8, FP16	489–694 tok/s
M1 · 16 GB unified	Q4_K_M, Q8, FP16	Evidence unavailable: no cited memory bandwidth for this hardware
M1 Pro · 16 GB unified	Q4_K_M, Q8, FP16	107–153 tok/s
M2 · 16 GB unified	Q4_K_M, Q8, FP16	53–77 tok/s
M2 Pro · 16 GB unified	Q4_K_M, Q8, FP16	107–153 tok/s
M3 · 16 GB unified	Q4_K_M, Q8, FP16	53–77 tok/s
M4 · 16 GB unified	Q4_K_M, Q8, FP16	64–92 tok/s
RX 6800 XT · 16 GB	Q4_K_M, Q8, FP16	Evidence unavailable: no cited memory bandwidth for this hardware
M3 Pro · 18 GB unified	Q4_K_M, Q8, FP16	80–115 tok/s
M4 Pro · 24 GB unified	Q4_K_M, Q8, FP16	146–208 tok/s
RTX 3090 · 24 GB	Q4_K_M, Q8, FP16	502–713 tok/s
RTX 4090 · 24 GB	Q4_K_M, Q8, FP16	541–767 tok/s
RX 7900 XTX · 24 GB	Q4_K_M, Q8, FP16	Evidence unavailable: no cited memory bandwidth for this hardware
M1 Max · 32 GB unified	Q4_K_M, Q8, FP16	214–305 tok/s
M2 Max · 32 GB unified	Q4_K_M, Q8, FP16	214–305 tok/s
M3 Max · 48 GB unified	Q4_K_M, Q8, FP16	161–229 tok/s
M4 Max · 48 GB unified	Q4_K_M, Q8, FP16	220–312 tok/s
M4 Pro · 48 GB unified	Q4_K_M, Q8, FP16	146–208 tok/s
Instinct MI210 · 64 GB	Q4_K_M, Q8, FP16	Evidence unavailable: no cited memory bandwidth for this hardware
M4 Max · 64 GB unified	Q4_K_M, Q8, FP16	220–312 tok/s

Speeds are estimates from memory bandwidth and weight size, not measured benchmarks. A price is the cheapest listed offer for that hardware.

Template details

Rating: No ratings yet
Runs: 0
Min VRAM: 3.8 GB
Backend: Set by the machine you pick
Weights: 1.1 GB
Version: llamacpp-qwen2-5-coder-1-5b-abliterated-v1.0.0
Image digest: 1f4b9cf58982…
Health check: SSH probe on the leased endpoint

We match GPUs on their measured runtime and dedicated VRAM. A hardware report doesn't qualify another vendor's backend.

#llm #chat #openai-api #gguf #uncensored #abliterated #coding

Reviews

No reviews yet.