RE

ReflectionCoder-CL-34B

ReflectioncoderGGUF by mradermacherUpdated 2024-08-02
Download on Hugging Face
Parameters33.7B
Context16K
Layers48
Architecturellama
Smallest quant7.3 GB
Quick answer

ReflectionCoder-CL-34B needs about 22.3 GB of memory at Q4_K_M (a 20.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 21 quants, from 7.3 GB (IQ1_S) to 27.7 GB (Q6_K).

34B parameter Llama model specialized for code generation

ReflectionCoder-CL-34B is a 34 billion‑parameter Llama architecture model trained for one‑off code generation. It uses reflection sequences with compiler feedback to improve coding accuracy. The model is released under Apache‑2.0 and supports 16 k context tokens.

Good at

  • One‑off code generation
  • Learning from compiler feedback
  • Large context handling

Limits

  • No vision support
  • Requires large VRAM for higher‑quality quants
  • License is Apache‑2.0

Best for

  • Writing complex scripts
  • Debugging code snippets
  • Generating code from specifications

Who it’s for. Developers and researchers needing high‑quality code generation in a local LLM setup. The model is suitable for environments where privacy or offline inference is required.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S7.3 GB 9.4 GB
Too big Get file →
IQ1_M7.9 GB 10.0 GB
Too big Get file →
IQ2_XXS9.0 GB 11.1 GB
Too big Get file →
IQ2_XS10.0 GB 12.1 GB
Too big Get file →
IQ2_S10.6 GB 12.7 GB
Too big Get file →
IQ2_M11.5 GB 13.6 GB
Too big Get file →
Q2_K12.5 GB 14.6 GB
Too big Get file →
IQ3_XXS13.0 GB 15.1 GB
Too big Get file →
IQ3_XS13.9 GB 16.0 GB
Too big Get file →
Q3_K_S14.6 GB 16.7 GB
Too big Get file →
IQ3_S14.7 GB 16.8 GB
Too big Get file →
IQ3_M15.2 GB 17.3 GB
Too big Get file →
Q3_K_M16.3 GB 18.4 GB
Too big Get file →
Q3_K_L17.8 GB 19.9 GB
Too big Get file →
IQ4_XS18.1 GB 20.2 GB
Too big Get file →
Q4_019.1 GB 21.2 GB
Too big Get file →
Q4_K_S19.2 GB 21.3 GB
Too big Get file →
Q4_K_M20.2 GB 22.3 GB
Too big Get file →
Q5_K_S23.2 GB 25.3 GB
Too big Get file →
Q5_K_M23.8 GB 25.9 GB
Too big Get file →
Q6_K27.7 GB 29.8 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (7.25 GB file, ~9.4 GB memory). With 12 GB VRAM IQ2_XS (10.02 GB file, ~12.1 GB memory) is a good balance. For 16 GB VRAM IQ3_XS (13.88 GB file, ~16 GB memory) offers higher quality while staying within limits. Estimates are approximate.

What GPU do you need for ReflectionCoder-CL-34B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ3_XS (13.9 GB file, about 16.0 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (20.2 GB file, about 22.3 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.7 GB file, about 29.8 GB in use).

Which ReflectionCoder-CL-34B quant should you choose?

Q4_K_M is the usual starting point for ReflectionCoder-CL-34B: it balances file size and quality well. Here it is a 20.2 GB file.

If memory is tight, the smallest file is IQ1_S at 7.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters33.7B
Layers48
Trained context16,384 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)3,870
Last updated2024-08-02

Frequently asked questions about ReflectionCoder-CL-34B

How much VRAM does ReflectionCoder-CL-34B need?

About 22.3 GB at Q4_K_M with an 8K context window. That is the 20.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run ReflectionCoder-CL-34B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ReflectionCoder-CL-34B GGUF?

It depends on the quant: IQ1_S is 7.3 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 10.0 GB, IQ2_S is 10.6 GB, IQ2_M is 11.5 GB and 15 more.

What context length does ReflectionCoder-CL-34B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 1.6 GB at 8K and 3.2 GB at 16K.

Where can I download ReflectionCoder-CL-34B GGUF?

The files are on Hugging Face in the mradermacher/ReflectionCoder-CL-34B-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ReflectionCoder-CL-34B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run ReflectionCoder-CL-34B on 8 GB VRAM?

Use the IQ1_S quant which requires about 9.4 GB of VRAM at 8 k context. It is the smallest quant available.

Does the model support image inputs?

No, the model is purely text‑based and has no vision capabilities.

What is the maximum context length?

The model supports up to 16 384 tokens of context.

Other GGUFs of ReflectionCoder-CL-34B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Reflectioncoder models

All Reflectioncoder →

Other medium models

All medium models →