RE

ReflectionCoder-DS-33B

ReflectioncoderGGUF by mradermacherUpdated 2024-05-30
Download on Hugging Face
Parameters33.3B
Context16K
Layers62
Architecturellama
Smallest quant12.4 GB
Quick answer

ReflectionCoder-DS-33B needs about 22.5 GB of memory at Q4_K_M (a 19.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 10 quants, from 12.4 GB (Q2_K) to 35.4 GB (Q8_0).

ReflectionCoder-DS-33B: 33.3B llama model focused on code generation

ReflectionCoder-DS-33B is a 33.3B llama architecture model trained on 16384 context tokens. It specializes in coding tasks and is released under the apache-2.0 license. The model is available in multiple GGUF quantizations.

Good at

  • One-off code generation
  • Compiler feedback integration
  • Large context handling

Limits

  • No vision support
  • Requires 8k context for estimates
  • License is apache-2.0

Best for

  • Developers needing code generation
  • Educational coding tools
  • Research on reflection-based models

Who it’s for. Engineers and researchers who need a large language model capable of generating code with compiler feedback. The model is suitable for projects that can handle the memory requirements of a 33.3B llama model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K12.4 GB 14.9 GB
Too big Get file →
Q3_K_S14.4 GB 17.0 GB
Too big Get file →
IQ3_S14.5 GB 17.1 GB
Too big Get file →
IQ3_M15.0 GB 17.6 GB
Too big Get file →
Q3_K_M16.1 GB 18.7 GB
Too big Get file →
Q3_K_L17.6 GB 20.1 GB
Too big Get file →
Q4_K_S18.9 GB 21.5 GB
Too big Get file →
Q4_K_M19.9 GB 22.5 GB
Too big Get file →
Q6_K27.4 GB 29.9 GB
Too big Get file →
Q8_035.4 GB 38.0 GB
Too big Get file →

For 8 GB VRAM use Q2_K (12.35 GB file, 14.9 GB memory). For 16 GB VRAM use Q4_K_M (19.94 GB file, 22.5 GB memory). For 32 GB VRAM use Q6_K (27.35 GB file, 29.9 GB memory). Estimates are approximate.

What GPU do you need for ReflectionCoder-DS-33B?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is Q2_K (12.4 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q4_K_M (19.9 GB file, about 22.5 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (27.4 GB file, about 29.9 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (35.4 GB file, about 38.0 GB in use).

Which ReflectionCoder-DS-33B quant should you choose?

Q4_K_M is the usual starting point for ReflectionCoder-DS-33B: it balances file size and quality well. Here it is a 19.9 GB file.

The Q8_0 file is 35.4 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 12.4 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
Parameters33.3B
Layers62
Trained context16,384 tokens
KV cache (fp16)248 KB per token

Source

Quantized bymradermacher
Licenseapache-2.0
Downloads (HF)1,198
Last updated2024-05-30

Frequently asked questions about ReflectionCoder-DS-33B

How much VRAM does ReflectionCoder-DS-33B need?

About 22.5 GB at Q4_K_M with an 8K context window. That is the 19.9 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-DS-33B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ReflectionCoder-DS-33B GGUF?

It depends on the quant: Q2_K is 12.4 GB, Q3_K_S is 14.4 GB, IQ3_S is 14.5 GB, IQ3_M is 15.0 GB, Q3_K_M is 16.1 GB, Q3_K_L is 17.6 GB and 4 more.

What context length does ReflectionCoder-DS-33B support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.1 GB at 8K and 4.2 GB at 16K.

Where can I download ReflectionCoder-DS-33B GGUF?

The files are on Hugging Face in the mradermacher/ReflectionCoder-DS-33B-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-DS-33B 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-DS-33B on 8 GB VRAM?

Use the Q2_K quant which requires about 14.9 GB memory at 8k context, so 8 GB VRAM is insufficient.

What license does this model use?

The model is released under the apache-2.0 license.

Does this model support vision tasks?

No, the model only supports text and coding tasks.

Other GGUFs of ReflectionCoder-DS-33B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Reflectioncoder models

All Reflectioncoder →

Other medium models

All medium models →