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 22 quants, from 12.4 GB (Q2_K) to 35.4 GB (Q8_0).
ReflectionCoder DS 33B – a 33.3B parameter coding model
ReflectionCoder DS 33B is a 33.3B parameter llama architecture model focused on code generation. It was quantized by RichardErkhov and released under the apache-2.0 license. The model supports a 16384 token context window.
Good at
- One‑off code generation
- Compiler‑feedback enhanced coding
- Large context handling
Limits
- No vision support
- Large memory requirement for higher quants
- No mixture of experts
Best for
- Developers needing accurate code snippets
- Rapid prototyping of software modules
- Educational coding assistants
Who it’s for. Engineers and researchers who require a large‑parameter model for generating or reviewing code. The model is suitable for environments where a 16384 token context is beneficial.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 12.4 GB | 14.9 GB | Too big | Get file → | |
| IQ3_XS | 13.7 GB | 16.3 GB | Too big | Get file → | |
| Q3_K_S | 14.4 GB | 17.0 GB | Too big | Get file → | |
| IQ3_S | 14.5 GB | 17.1 GB | Too big | Get file → | |
| IQ3_M | 15.0 GB | 17.6 GB | Too big | Get file → | |
| Q3_K | 16.1 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_M | 16.1 GB | 18.7 GB | Too big | Get file → | |
| Q3_K_L | 17.6 GB | 20.1 GB | Too big | Get file → | |
| IQ4_XS | 18.0 GB | 20.6 GB | Too big | Get file → | |
| Q4_0 | 18.8 GB | 21.4 GB | Too big | Get file → | |
| Q4_K_S | 18.9 GB | 21.5 GB | Too big | Get file → | |
| IQ4_NL | 19.0 GB | 21.6 GB | Too big | Get file → | |
| Q4_K | 19.9 GB | 22.5 GB | Too big | Get file → | |
| Q4_K_M | 19.9 GB | 22.5 GB | Too big | Get file → | |
| Q4_1 | 20.9 GB | 23.5 GB | Too big | Get file → | |
| Q5_0 | 23.0 GB | 25.5 GB | Too big | Get file → | |
| Q5_K_S | 23.0 GB | 25.5 GB | Too big | Get file → | |
| Q5_K | 23.5 GB | 26.1 GB | Too big | Get file → | |
| Q5_K_M | 23.5 GB | 26.1 GB | Too big | Get file → | |
| Q5_1 | 25.0 GB | 27.6 GB | Too big | Get file → | |
| Q6_K | 27.4 GB | 29.9 GB | Too big | Get file → | |
| Q8_0 | 35.4 GB | 38.0 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (12.35 GB file, ~14.9 GB memory). For 12 GB VRAM, Q3_K_S (14.42 GB file, ~17 GB memory). For 16 GB VRAM, Q4_K (19.94 GB file, ~22.5 GB memory).
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_1 (20.9 GB file, about 23.5 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
Source
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, IQ3_XS is 13.7 GB, Q3_K_S is 14.4 GB, IQ3_S is 14.5 GB, IQ3_M is 15.0 GB, Q3_K is 16.1 GB and 16 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 RichardErkhov/SenseLLM_-_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 Q2_K on 8 GB VRAM?
Yes, Q2_K requires approximately 14.9 GB memory at 8k context, which fits within 8 GB VRAM when using efficient batching.
Does the model support image inputs?
No, ReflectionCoder DS 33B does not support vision or image inputs.
What license does the model use?
The model is released under the apache-2.0 license.